© 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. 3050
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return (negative activations)

    python-code · gemini-2.5-flash-lite

    method assignment or function parameter

    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
     },↵
    -0.07
     ]↵
    -0.06
     """↵
    -0.04
    .start
    -0.04
     start
    -0.04
     cur
    -0.04
     u
    -0.04
     }↵
    -0.04
     source
    -0.04
    start
    -0.04
    POSITIVE LOGITS
     match
    0.06
    atch
    0.04
    [p
    0.04
     This
    0.04
    (p
    0.04
     pattern
    0.04
    _pattern
    0.04
    _part
    0.04
     sele
    0.03
     part
    0.03
    Activations Density 46.423%

    No Known Activations