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

    Neuronpedia

    INDEX
    Explanations

    informative way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Temmuz
    0.54
    十
    0.54
    新型コロナ
    0.46
     tutaj
    0.45
    特朗普
    0.44
     十
    0.44
     Soldaten
    0.44
    Ҭ
    0.43
    툐
    0.43
     Тут
    0.43
    POSITIVE LOGITS
     पांच
    0.51
    Vì
    0.47
     Vì
    0.45
    Vector
    0.43
    മായി
    0.40
     Akan
    0.38
     város
    0.38
     ไป
    0.38
    かなり
    0.38
     இணை
    0.37
    Act Density 0.075%

    No Known Activations