© 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. 7399
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    list item or variable name

    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
    umn
    -0.03
    é
    -0.02
    æ
    -0.02
    å
    -0.02
    è
    -0.02
    ä
    -0.02
    ç
    -0.02
    ã
    -0.02
    .name
    -0.01
    .id
    -0.01
    POSITIVE LOGITS
     form
    0.03
    _set
    0.02
    reshold
    0.02
     en
    0.01
    vai
    0.01
    uel
    0.01
    endoftext
    0.01
    _scores
    0.01
     or
    0.01
     of
    0.01
    Activations Density 85.896%

    No Known Activations