© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3367
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import tkinter as tk

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     process
    -0.05
    al
    -0.02
    old
    -0.02
    als
    -0.02
    's
    -0.02
    ary
    -0.02
    all
    -0.02
    ra
    -0.01
    ject
    -0.01
    ual
    -0.01
    POSITIVE LOGITS
    o
    0.07
    tes
    0.06
    ters
    0.06
    te
    0.05
    ter
    0.05
    tive
    0.05
    onent
    0.05
    ts
    0.04
    ted
    0.04
    onents
    0.04
    Activations Density 72.119%

    No Known Activations