© 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. 2-MLP
    11. 7089
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    chr

    python-code · gemini-2.5-flash-lite

    assignment after if (negative activations)

    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
    ample
    -0.04
    als
    -0.04
    direction
    -0.04
    ot
    -0.03
     moves
    -0.03
    turn
    -0.03
    mmand
    -0.03
     move
    -0.03
     math
    -0.03
    and
    -0.03
    POSITIVE LOGITS
     ('
    0.05
    ]['
    0.05
    ['
    0.05
     {'
    0.05
     ['
    0.04
    ·
    0.04
     '
    0.04
    ='
    0.04
    ters
    0.04
    ('
    0.04
    Activations Density 100.000%

    No Known Activations