© 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. 6080
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to string literal list (negative activations)

    python-code · gemini-2.5-flash-lite

    closing parenthesis followed by statement

    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
    alculate
    -0.04
    enerate
    -0.03
     calculate
    -0.03
     find
    -0.03
     parse
    -0.03
     generate
    -0.03
     create
    -0.03
    .append
    -0.02
     Calculate
    -0.02
    ulate
    -0.02
    POSITIVE LOGITS
     found
    0.05
    ;
    0.04
     break
    0.04
    ):↵
    0.03
    over
    0.02
    ]):↵
    0.02
     while
    0.02
    _move
    0.02
     th
    0.02
    ")
    0.01
    Activations Density 76.291%

    No Known Activations