Neural Playground

Sandboxes

No wrong answers here — slide the knobs and watch what the little network does.

What Can a Tiny Brain Decide?

Drag the glowing point around. The background shows what the little network thinks: blue means 'yes' and orange means 'no'. Move the sliders to change what it believes.

Sigmoid activation2 hidden neurons

Imagine sorting animals: Class A = cats 🐱 (blue circles), Class B = dogs 🐶 (orange crosses). Every dot on the map is one example. The network draws a line that tries to separate cats from dogs — drag the point to see which side it lands on.

Network says: Class A (e.g. cats 🐱)
confidence 73%
Class A (e.g. cats 🐱)
Class B (e.g. dogs 🐶)
Neuron firing
N1
N2

Drag the point on the canvas to test the network anywhere.

Control knobs

Activation Curve Playground

See how ReLU, Sigmoid and Tanh bend the same input. Slide the input dot along the curve and watch the output value change.

ReLU activation1 hidden neuron

A neuron first multiplies its input by a weight and adds a bias. The activation function is the last step: it decides the shape of the 'boom'. Gain stretches the input before the curve sees it.

input
1.00
gain
1.00
output
1.00

Control knobs

Make the Neurons Glow

A tiny 2-2-1 network. Push the inputs and bias around to light up the neurons. Brighter nodes are firing harder, and the connections pulse with their strength.

Tanh activation2 hidden neurons
Output value (Tanh): 0.377

Control knobs

Signal Tracer — Follow the Numbers

Type inputs, click any connection to edit its weight, then watch the actual numbers flow: input → ×weight → sum + bias → activation → output.

Tanh activationeditable inputs · weights · layers

This is the whole network with the lid off. Every line shows the signal travelling through it, every neuron shows its value, and you can rewire any weight or add hidden layers. Press Step to walk through one layer at a time.

Type the input values

Activation

Hidden layers

Hidden 13
Hidden 23

Connection weight

Click any line in the diagram to edit its weight.

Output -0.915