© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5616
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function definition body

    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
    .index
    -0.05
     |
    -0.04
     range
    -0.04
    ģ
    -0.04
     heapq
    -0.03
    ]['
    -0.03
     /
    -0.03
     {'
    -0.03
     {"
    -0.03
     graph
    -0.03
    POSITIVE LOGITS
    gy
    0.06
     while
    0.05
    _path
    0.04
    :-
    0.04
    .write
    0.04
    alculate
    0.04
    append
    0.04
     iter
    0.04
    g
    0.03
    __
    0.03
    Activations Density 76.251%

    No Known Activations