© 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. 3386
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    nested attribute access

    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
     import
    -0.08
    **
    -0.07
     **
    -0.07
     represent
    -0.03
    <
    -0.03
    \
    -0.03
    ilename
    -0.03
     Example
    -0.03
     Returns
    -0.03
     represe
    -0.03
    POSITIVE LOGITS
     as
    0.08
    ome
    0.05
    len
    0.05
     break
    0.04
     False
    0.03
    col
    0.03
    rint
    0.03
    ].
    0.03
    ush
    0.03
     that
    0.03
    Activations Density 9.542%

    No Known Activations