© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4523
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    execute method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    sqlite3.connect or asyncio.run

    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
     &
    -0.03
    one
    -0.00
    pe
    -0.00
    use
    -0.00
    per
    -0.00
    ut
    -0.00
    f
    -0.00
     if
    -0.00
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
    [-
    0.12
     and
    0.06
     [-
    0.05
     two
    0.03
     are
    0.03
     +
    0.03
     the
    0.03
    ][
    0.02
    }
    0.02
     <
    0.02
    Activations Density 93.018%

    No Known Activations