© 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. 4467
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    preceding or following list/array indices (negative activations)

    python-code · gemini-2.5-flash-lite

    'in' keyword with range

    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
    distances
    -0.05
     distances
    -0.04
    sen
    -0.04
    jac
    -0.04
    _distances
    -0.04
    etween
    -0.04
    distan
    -0.04
     Calculate
    -0.04
     +
    -0.03
    arget
    -0.03
    POSITIVE LOGITS
    ","
    0.05
    get
    0.05
    ",
    0.04
    ',
    0.04
     get
    0.03
     ((
    0.03
    ")↵
    0.03
     us
    0.03
    .get
    0.03
     ",
    0.03
    Activations Density 99.998%

    No Known Activations