© 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. 7695
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    analysis_percentAlternatively: `format()` callOr: `str` literal string (negative activations)

    python-code · gemini-2.5-flash-lite

    sm module import

    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
    §
    -0.06
    cell
    -0.06
    node
    -0.06
    udent
    -0.05
    _cell
    -0.05
    ity
    -0.05
    erson
    -0.05
    (point
    -0.05
    tem
    -0.05
     cell
    -0.05
    POSITIVE LOGITS
    ½
    0.03
    unt
    0.03
     command
    0.03
    count
    0.02
    ount
    0.02
     count
    0.02
    _counts
    0.02
    _count
    0.02
    unter
    0.01
     qu
    0.01
    Activations Density 97.758%

    No Known Activations