© 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. 5564
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation or multiplication assignment

    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
    ×
    -0.08
    Ø
    -0.07
    ä
    -0.07
    ã
    -0.07
    87
    -0.07
    ç
    -0.07
    é
    -0.07
    |>
    -0.06
    æ
    -0.06
    å
    -0.06
    POSITIVE LOGITS
    :
    0.04
    :",
    0.03
    =None
    0.03
    =True
    0.03
    ()
    0.03
     ->
    0.03
    timal
    0.03
    losest
    0.03
    =lambda
    0.03
    :-
    0.03
    Activations Density 69.712%

    No Known Activations