© 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. 3283
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    return value from function (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment or `None` check

    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
    -0.04
    -0.04
    Ģ
    -0.02
    ↵            ↵
    -0.02
    -0.02
        ↵
    -0.01
    16
    -0.01
    j
    -0.01
    17
    -0.01
    end
    -0.01
    POSITIVE LOGITS
    rent
    0.02
    ous
    0.02
    ari
    0.02
    0.02
    0.01
    ure
    0.01
    th
    0.01
    .txt
    0.01
    `
    0.01
    ree
    0.01
    Activations Density 55.196%

    No Known Activations