© 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. 5569
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of function call or definition (negative activations)

    python-code · gemini-2.5-flash-lite

    comma in a list or tuple

    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
     Create
    -0.03
    itial
    -0.03
    ="
    -0.03
     ('
    -0.03
     ("
    -0.03
    ='
    -0.03
    stance
    -0.03
     Initialize
    -0.02
     ['
    -0.02
     ".
    -0.02
    POSITIVE LOGITS
    .de
    0.01
    X
    0.01
     Y
    0.01
    }")<|
    0.01
     last
    0.01
    Y
    0.01
    Z
    0.01
     O
    0.01
    unc
    0.01
     in
    0.01
    Activations Density 98.098%

    No Known Activations