© 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. 7369
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `with` statement or `yield` keyword (negative activations)

    python-code · gemini-2.5-flash-lite

    yield keyword or y variable

    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
     target
    -0.04
    (s
    -0.03
    arget
    -0.03
    ilen
    -0.03
    set
    -0.03
    um
    -0.02
     zip
    -0.02
    str
    -0.02
    List
    -0.02
    _ids
    -0.02
    POSITIVE LOGITS
    _row
    0.03
    e
    0.03
    is
    0.03
    row
    0.03
    we
    0.03
    Y
    0.03
     rows
    0.02
     row
    0.02
    es
    0.02
    (row
    0.02
    Activations Density 74.333%

    No Known Activations