© 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. 7317
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment in lists (negative activations)

    python-code · gemini-2.5-flash-lite

    numbers in integer literals

    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
    (len
    -0.07
     are
    -0.06
    qrt
    -0.05
     len
    -0.05
    len
    -0.04
     abs
    -0.04
     algorithm
    -0.03
    ab
    -0.03
     function
    -0.03
    verage
    -0.03
    POSITIVE LOGITS
    over
    0.10
    term
    0.08
    zero
    0.08
     char
    0.06
     each
    0.06
     representing
    0.05
    ne
    0.04
    inal
    0.04
    ative
    0.03
     ele
    0.03
    Activations Density 99.997%

    No Known Activations