© 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. 7405
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class 'a' constructor

    python-code · gemini-2.5-flash-lite

    `return` keyword or `]]` syntax (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
    gth
    -0.07
    utation
    -0.07
    class
    -0.06
    Ĥ
    -0.05
    essage
    -0.05
     whe
    -0.05
    us
    -0.04
    xF
    -0.04
    ry
    -0.04
     step
    -0.04
    POSITIVE LOGITS
    ency
    0.11
    umn
    0.11
    timal
    0.11
    straints
    0.10
    jective
    0.10
    itial
    0.10
    rib
    0.09
    pected
    0.09
    straint
    0.08
    lauses
    0.08
    Activations Density 100.000%

    No Known Activations