© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5232
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    index in loop (negative activations)

    python-code · gemini-2.5-flash-lite

    constructor or dunder methods

    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
    ameters
    -0.03
    structions
    -0.03
    .values
    -0.02
    endencies
    -0.02
     *
    -0.02
     {}↵
    -0.02
    *
    -0.02
    tes
    -0.01
    .items
    -0.01
     **
    -0.01
    POSITIVE LOGITS
     other
    0.05
     between
    0.04
    mmon
    0.04
     two
    0.04
    wo
    0.03
     continue
    0.03
    [neighbor
    0.03
    V
    0.02
    neighbor
    0.02
     V
    0.02
    Activations Density 99.993%

    No Known Activations