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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on programming-language import declarations (e.g. Java “import …” statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     transportation
    -0.07
     evacuate
    -0.06
     ثم
    -0.06
    谱
    -0.06
    جي
    -0.06
     graft
    -0.06
     determination
    -0.06
     families
    -0.06
     Plum
    -0.06
    ‌رس
    -0.06
    POSITIVE LOGITS
    ：“
    0.06
    square
    0.06
     carg
    0.06
    ertype
    0.06
    IMPORTANT
    0.06
     nomine
    0.06
     Boolean
    0.06
    shield
    0.06
    036
    0.06
     WARRANTIES
    0.06
    Act Density 0.047%

    No Known Activations