© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6852
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `os.path.exists` or `os.listdir`

    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
    The
    -0.08
    iven
    -0.06
     The
    -0.05
    =
    -0.04
    ='
    -0.04
    ="
    -0.04
     This
    -0.04
    ffe
    -0.04
    87
    -0.04
    1
    -0.04
    POSITIVE LOGITS
    xt
    0.06
     q
    0.05
    q
    0.04
    text
    0.04
    __':↵
    0.04
    ast
    0.03
    ':↵
    0.03
    ':
    0.03
    ind
    0.03
    '),
    0.03
    Activations Density 19.804%

    No Known Activations