© 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. 2119
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment, list literal, function definition (negative activations)

    python-code · gemini-2.5-flash-lite

    string concatenation operator after expression

    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
    -0.05
    (re
    -0.04
    Ģ
    -0.03
    ↵            ↵
    -0.03
    -0.03
     as
    -0.02
    -0.02
        ↵
    -0.02
    ","
    -0.02
    POSITIVE LOGITS
     Tuple
    0.02
    ush
    0.02
    hor
    0.02
    append
    0.02
    ()
    0.02
    .txt
    0.02
    `
    0.02
    ":
    0.02
     add
    0.01
    add
    0.01
    Activations Density 99.923%

    No Known Activations