Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on comment lines that describe planned changes or tasks (e.g., TODOs and “will …” statements) rather than on regular code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     KA
    -0.07
     championships
    -0.07
     platinum
    -0.06
     Judith
    -0.06
     institutional
    -0.06
     disruptions
    -0.06
    泉
    -0.06
    Bluetooth
    -0.06
     查询
    -0.06
    อส
    -0.06
    POSITIVE LOGITS
    driver
    0.07
    paced
    0.07
     işlemi
    0.06
     conco
    0.06
    piel
    0.06
    .getItems
    0.06
    teş
    0.06
    /portfolio
    0.06
     griev
    0.06
     음
    0.06
    Act Density 0.066%

    No Known Activations