Home▸Society & Economics▸Explainable AI: Opening the Black Box of Model Decisions

🧠 Explainable AI: Opening the Black Box

An interactive 3D neural network where feeding in a sample input reveals simulated feature-attribution highlights, like SHAP values, showing which inputs most influenced the model's decision.

Society & Economics3DModerate60 FPS

A small feed-forward network decides whether to approve or deny a loan applicant. Feeding in different sample inputs recomputes real occlusion-based feature attributions — a SHAP-adjacent technique — and lights up the exact nodes and edges that pushed the decision toward Approve or Deny.

🔬 What It Demonstrates

Each node's glow is computed by zeroing that node and re-running the network downstream, then measuring how much the output probability changed — the same "remove it and see what happens" logic behind SHAP and occlusion sensitivity.

🎮 How to Use

Pick an applicant sample or drag the Income / Debt ratio sliders to build a custom profile. Raise the attribution threshold to strip away weak connections and isolate only the strongest reasoning paths, then replay the forward pass to watch the signal travel layer by layer.

💡 Did You Know?

True SHAP values average a feature's marginal contribution across every possible ordering of features — computationally expensive for large models, which is why fast approximations like this one are common in practice.

⚙ Under the hood

Interactive 3D neural network where feeding in a sample input shows simulated feature-attribution highlights, like SHAP values, revealing which inputs most influenced the model's decision.

explainable-aiinterpretabilityshap-valuesmodel-transparencymachine-learningsociety

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install