© 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. 7467
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .g group or .g generate

    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
    lf
    -0.05
     dfs
    -0.04
    lace
    -0.04
    lass
    -0.04
    l
    -0.04
    ls
    -0.03
    right
    -0.03
    ro
    -0.03
    ag
    -0.03
    Ö
    -0.03
    POSITIVE LOGITS
    !
    0.04
    get
    0.04
    1
    0.03
    ..
    0.03
    ?
    0.03
     [
    0.03
    kets
    0.03
    ...
    0.03
    _with
    0.03
    etween
    0.03
    Activations Density 79.195%

    No Known Activations