← Back to AI Foundations
High School Lab

Neural Net Internals Explorer

Inspect every weight and activation of a small network — then train it with real gradient descent.

Activation Function

σ(z) = 1 / (1 + e⁻ᶻ) — smooth, output in (0, 1), derivative = a(1−a)

Input Values

0.000
1.000

Input → Hidden Weights (W)

-0.795
0.230
0.125
-0.605
0.202
-0.550

Hidden Biases (b_h)

0.088
0.229
0.157

Hidden → Output Weights (v)

0.145
-0.246
0.234

Output Bias (b_o)

0.014

Network Diagram

Line thickness = |weight|; cyan = positive, red = negative. Circle fill = activation level.

Live Activations

Inputs: x₁ = 0.000, x₂ = 1.000

Hidden Layer

h1: z = -0.5162a = 0.3737
h2: z = 0.4310a = 0.6061
h3: z = -0.3922a = 0.4032

Output

z_o = 0.0130ŷ = 0.5032

The Math (Forward Pass)

For each hidden neuron j (1..3):

z_j = w[x1→hj]·x1 + w[x2→hj]·x2 + b_hj

a_j = act(z_j)

Output:

z_o = v1·a1 + v2·a2 + v3·a3 + b_o

ŷ = act(z_o)