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

    Neuronpedia

    INDEX
    Explanations

    Zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    关羽
    -0.07
    茝
    -0.07
    �
    -0.07
    豹
    -0.07
    BundleOrNil
    -0.07
    䶮
    -0.07
    ombine
    -0.07
    嵝
    -0.07
    刬
    -0.07
     İsl
    -0.07
    POSITIVE LOGITS
    購買
    0.08
     payroll
    0.07
     Grocery
    0.07
     distinguish
    0.07
    �
    0.07
     classrooms
    0.07
    基督教
    0.07
     clarified
    0.07
    ::::::::
    0.07
     internal
    0.07
    Act Density 0.002%

    No Known Activations