© 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. 6760
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    index 0

    python-code · gemini-2.5-flash-lite

    .p attribute access or method calls (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
     whe
    -0.03
    us
    -0.02
     P
    -0.02
     step
    -0.02
    of
    -0.02
     pro
    -0.02
    idth
    -0.02
    _in
    -0.02
    ame
    -0.02
    he
    -0.01
    POSITIVE LOGITS
    join
    0.04
    rib
    0.04
    umn
    0.04
    ber
    0.03
    ry
    0.03
    ulation
    0.03
    µ
    0.03
    ion
    0.03
    atri
    0.03
     each
    0.03
    Activations Density 100.000%

    No Known Activations