© 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. 6-MLP
    11. 6904
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `=` and `==` operators (negative activations)

    python-code · gemini-2.5-flash-lite

    for loops with variable i

    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
    mport
    -0.05
    None
    -0.05
     []↵
    -0.05
     return
    -0.05
    rint
    -0.05
    alse
    -0.05
     None
    -0.04
    re
    -0.04
     []↵↵
    -0.04
     False
    -0.04
    POSITIVE LOGITS
     Calculate
    0.05
    distances
    0.05
     Find
    0.04
    jac
    0.04
    erge
    0.04
    _distances
    0.04
    etween
    0.04
    distan
    0.04
     based
    0.04
     distances
    0.03
    Activations Density 99.917%

    No Known Activations