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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2301
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    call arguments and function definitions (negative activations)

    python-code · gemini-2.5-flash-lite

    `re.match` calls

    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
     &
    -0.01
    ["
    -0.01
     line
    -0.01
    .txt
    -0.00
    `
    -0.00
    ":
    -0.00
     set
    -0.00
    out
    -0.00
    cell
    -0.00
    ate
    -0.00
    POSITIVE LOGITS
     Returns
    0.05
     Return
    0.05
     return
    0.04
    turn
    0.03
     raise
    0.03
    urn
    0.02
     :
    0.02
    0.02
    :
    0.02
    )],↵
    0.01
    Activations Density 99.792%

    No Known Activations