© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4127
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method parameter lists (negative activations)

    python-code · gemini-2.5-flash-lite

    closing parenthesis of a class definition

    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
     representing
    -0.06
    reshold
    -0.05
    vai
    -0.04
    uel
    -0.04
    endoftext
    -0.03
     that
    -0.03
     given
    -0.03
    _scores
    -0.03
     each
    -0.03
     the
    -0.03
    POSITIVE LOGITS
     \
    0.03
    ;
    0.01
    da
    0.01
    ):↵
    0.01
    init
    0.01
    ]):↵
    0.01
    is
    0.01
    ")
    0.00
    <extra_output_id:2047>
    0.00
    _row
    0.00
    Activations Density 74.512%

    No Known Activations