© 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. 7179
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or subtraction (negative activations)

    python-code · gemini-2.5-flash-lite

    xml.etree.ElementTree import

    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
    (row
    -0.01
    ven
    -0.01
    -0.01
    ti
    -0.01
    @
    -0.00
    ress
    -0.00
    urn
    -0.00
     on
    -0.00
     items
    -0.00
     ad
    -0.00
    POSITIVE LOGITS
    prese
    0.03
    e
    0.03
    es
    0.02
     dictionary
    0.01
    ctionary
    0.01
     second
    0.01
    uple
    0.01
    ed
    0.01
     deque
    0.01
     dict
    0.01
    Activations Density 89.208%

    No Known Activations