© 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. 2605
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list indexing or attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    .right attribute

    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
     Create
    -0.02
    _map
    -0.01
    itial
    -0.01
    _matrix
    -0.01
    _queue
    -0.01
    stance
    -0.01
     Initialize
    -0.01
    _dict
    -0.01
     defaultdict
    -0.01
    .graph
    -0.01
    POSITIVE LOGITS
    .split
    0.02
    split
    0.01
    .read
    0.01
    .strip
    0.01
    ake
    0.01
    strip
    0.01
    isit
    0.01
    .find
    0.01
    ain
    0.01
    im
    0.01
    Activations Density 94.166%

    No Known Activations