© 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. 2461
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing brace followed by opening brace

    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
     range
    -0.05
     represe
    -0.05
    hildren
    -0.04
    _range
    -0.04
    ange
    -0.04
    range
    -0.04
     ->
    -0.03
     whe
    -0.03
    ameters
    -0.03
    structions
    -0.03
    POSITIVE LOGITS
    ctionary
    0.03
     deque
    0.03
     dictionary
    0.03
     dict
    0.03
     Tuple
    0.03
    er
    0.03
     List
    0.03
    _dict
    0.03
     tuple
    0.03
    dict
    0.03
    Activations Density 75.641%

    No Known Activations