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

    Neuronpedia

    INDEX
    Explanations

    makes coding/development faster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supplémentaire
    2.15
    ंत्रिक
    2.01
     pois
    1.99
     રહ્યા
    1.96
    ฿
    1.96
     toga
    1.93
    łącznie
    1.92
    લ
    1.91
    Исход
    1.91
    লা
    1.87
    POSITIVE LOGITS
     ढंग
    2.54
    样的
    2.54
    ن
    2.46
    hift
    2.28
    ्य
    2.22
    al
    2.21
    ۥ
    2.18
    ︎
    2.15
    おり
    2.13
    𝘤
    2.13
    Act Density 0.084%

    No Known Activations