© 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. 3098
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal or function call

    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
    ateg
    -0.06
     any
    -0.04
    .start
    -0.04
     start
    -0.04
    otal
    -0.04
    timal
    -0.03
    losest
    -0.03
     source
    -0.03
    start
    -0.03
     True
    -0.03
    POSITIVE LOGITS
    jkstra
    0.04
     initial
    0.04
    _f
    0.04
    .remove
    0.04
    }")<|
    0.03
    ~
    0.03
    uild
    0.03
    G
    0.03
     con
    0.03
     This
    0.03
    Activations Density 36.875%

    No Known Activations