© 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. 5154
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    star unpacking argument (negative activations)

    python-code · gemini-2.5-flash-lite

    underscore then keyword or function name

    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
    .strip
    -0.03
    anage
    -0.02
    000
    -0.02
    olver
    -0.02
    _id
    -0.02
    .
    -0.02
    0
    -0.02
     [
    -0.01
    sert
    -0.01
    uil
    -0.01
    POSITIVE LOGITS
    =True
    0.08
    _and
    0.03
     state
    0.02
    he
    0.02
     he
    0.02
    si
    0.02
    _info
    0.02
     ele
    0.01
    mple
    0.01
     range
    0.01
    Activations Density 73.589%

    No Known Activations