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

    Neuronpedia

    INDEX
    Explanations

    data types in code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.81
    使用
    0.72
    （
    0.68
    最大
    0.66
    柠檬
    0.65
     (
    0.63
    关系
    0.63
    ки
    0.62
     Base
    0.62
     a
    0.62
    POSITIVE LOGITS
    ing
    0.81
    .'
    0.66
    <unused2115>
    0.64
    $',
    0.63
    .',
    0.62
    ;
    0.62
    Sums
    0.61
    TimeDict
    0.61
    ເພື່ອ
    0.60
    .",
    0.59
    Act Density 0.006%

    No Known Activations