© 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. 3089
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple unpacking or function argument (negative activations)

    python-code · gemini-2.5-flash-lite

    list item access or unpacking

    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
    .values
    -0.04
    ax
    -0.03
    .items
    -0.03
    ron
    -0.03
    .keys
    -0.03
    _population
    -0.02
     heap
    -0.02
    otal
    -0.02
     dp
    -0.02
     heapq
    -0.02
    POSITIVE LOGITS
    _start
    0.04
     start
    0.04
    (start
    0.04
    _left
    0.04
     source
    0.04
    start
    0.04
    .start
    0.04
    irst
    0.04
     or
    0.04
     St
    0.03
    Activations Density 99.743%

    No Known Activations