© 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. 2330
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    module 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
    ilename
    -0.06
    _file
    -0.05
    (filename
    -0.05
     file
    -0.04
    ave
    -0.04
    (map
    -0.04
    ilen
    -0.04
    (y
    -0.04
    vai
    -0.04
    .write
    -0.04
    POSITIVE LOGITS
     {}↵↵
    0.06
     {}↵
    0.05
    apping
    0.04
    ur
    0.03
    un
    0.03
     defaultdict
    0.03
    ctionary
    0.03
     dict
    0.02
     []↵↵
    0.02
    ue
    0.02
    Activations Density 41.348%

    No Known Activations