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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4811
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list literal or indexing

    python-code · gemini-2.5-flash-lite

    `@property` decorator or `&` operator (negative activations)

    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
     Calculate
    -0.07
    etween
    -0.06
     dx
    -0.06
     abs
    -0.05
    ta
    -0.04
     math
    -0.04
    put
    -0.04
    ctionary
    -0.04
    90
    -0.04
    dividual
    -0.04
    POSITIVE LOGITS
    .add
    0.08
    gest
    0.05
    ied
    0.04
    ies
    0.04
    _value
    0.04
     Value
    0.04
    ė
    0.04
    ool
    0.04
     value
    0.04
     with
    0.04
    Activations Density 100.000%

    No Known Activations