© 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. 5069
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to name or value (negative activations)

    python-code · gemini-2.5-flash-lite

    alias after etree import

    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
    :↵
    -0.02
    .random
    -0.01
     Get
    -0.01
    inal
    -0.01
    result
    -0.01
    ault
    -0.01
     problem
    -0.01
    ?
    -0.01
     result
    -0.01
    _result
    -0.01
    POSITIVE LOGITS
    .append
    0.05
    mport
    0.05
     -=
    0.05
     return
    0.04
    <|
    0.04
    .remove
    0.04
    .add
    0.04
    _queue
    0.04
     +=
    0.04
     function
    0.04
    Activations Density 97.668%

    No Known Activations