© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 5912
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis

    python-code · gemini-2.5-flash-lite

    `random`.choice or `.` followed by identifier (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
    Ĥ
    -0.03
    Ĺ
    -0.02
     **
    -0.02
    graph
    -0.01
    **
    -0.01
    ak
    -0.01
    ı
    -0.01
    ust
    -0.01
     /
    -0.01
     *
    -0.01
    POSITIVE LOGITS
    ied
    0.08
    ative
    0.06
    ies
    0.06
    isi
    0.06
    endoftext
    0.05
    ange
    0.05
    ency
    0.05
    rack
    0.05
    utation
    0.05
    ues
    0.05
    Activations Density 100.000%

    No Known Activations