© 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. 7890
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable 'b' followed by ':' or ')' (negative activations)

    python-code · gemini-2.5-flash-lite

    finally keyword

    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
    ig
    -0.03
     set
    -0.02
    ci
    -0.02
    ust
    -0.02
    verage
    -0.02
     us
    -0.02
     between
    -0.02
     based
    -0.01
     on
    -0.01
    inary
    -0.01
    POSITIVE LOGITS
    y
    0.06
    Y
    0.05
    ies
    0.04
    yp
    0.04
    ied
    0.04
    ic
    0.03
    ines
    0.03
    one
    0.02
    ound
    0.02
    ip
    0.02
    Activations Density 96.035%

    No Known Activations