© 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. 2-MLP
    11. 7461
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing brace or bracket

    python-code · gemini-2.5-flash-lite

    method attribute access (negative activations)

    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
    ķ
    -0.02
    values
    -0.01
     del
    -0.01
    ode
    -0.01
    }"
    -0.01
    ak
    -0.01
    ok
    -0.01
     ",
    -0.01
    place
    -0.01
     ".
    -0.01
    POSITIVE LOGITS
    reshold
    0.04
    istic
    0.04
    sible
    0.03
    [str
    0.03
    ique
    0.03
    mpty
    0.03
    pected
    0.03
    tive
    0.03
    ange
    0.03
    ual
    0.03
    Activations Density 100.000%

    No Known Activations