© 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. 7389
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment ` var =` (negative activations)

    python-code · gemini-2.5-flash-lite

    f-string interpolation and contents

    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
     <=
    -0.06
     If
    -0.05
     >=
    -0.04
    lse
    -0.04
     Check
    -0.04
    lif
    -0.03
    ound
    -0.03
     if
    -0.03
    .is
    -0.03
     elif
    -0.03
    POSITIVE LOGITS
    jkstra
    0.03
     initial
    0.02
    ~
    0.02
    uild
    0.02
     con
    0.02
    %
    0.02
     read
    0.02
     generate
    0.01
     ob
    0.01
    ro
    0.01
    Activations Density 91.893%

    No Known Activations