© 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. 2325
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma and argument separator (negative activations)

    python-code · gemini-2.5-flash-lite

    list item access with square brackets

    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
     Example
    -0.04
     Testing
    -0.03
    ak
    -0.03
     Test
    -0.03
    ample
    -0.03
    iven
    -0.03
     [[
    -0.03
    em
    -0.02
    ilename
    -0.02
     Create
    -0.02
    POSITIVE LOGITS
     dictionary
    0.03
    ctionary
    0.03
    uple
    0.03
     deque
    0.03
     dict
    0.03
     Tuple
    0.03
     List
    0.02
    _dict
    0.02
     tuple
    0.02
    dict
    0.02
    Activations Density 89.660%

    No Known Activations