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

    Neuronpedia

    INDEX
    Explanations

    support for services, items, groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     passable
    0.79
     пользоваться
    0.75
    事
    0.74
     संके
    0.72
    कडे
    0.72
    offsetX
    0.70
    Pres
    0.69
    ্যোগ
    0.68
     გამოყენ
    0.68
    邀請
    0.68
    POSITIVE LOGITS
    iveness
    0.97
    ande
    0.89
    יה
    0.87
     көрс
    0.86
    тивное
    0.86
    랄
    0.83
    ive
    0.80
    믿
    0.80
    राम
    0.79
    笏
    0.78
    Act Density 0.142%

    No Known Activations