© 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. 5959
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string join method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment or equality check

    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
     range
    -0.09
    .keys
    -0.08
     enumerate
    -0.08
     set
    -0.08
    _range
    -0.07
    set
    -0.06
     ['
    -0.06
     ["
    -0.06
    ange
    -0.06
    range
    -0.06
    POSITIVE LOGITS
    ][
    0.04
    .find
    0.04
     find
    0.03
    .append
    0.03
     Find
    0.03
    ]][
    0.03
    ind
    0.02
    (map
    0.02
     represent
    0.02
    ran
    0.02
    Activations Density 91.980%

    No Known Activations