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

    Neuronpedia

    INDEX
    Explanations

    help with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ersion
    0.38
    而在
    0.36
    chodu
    0.36
    愔
    0.36
    ybės
    0.35
    튠
    0.35
     survivors
    0.35
    ूथ
    0.35
     Notiflix
    0.35
    Saver
    0.35
    POSITIVE LOGITS
     Nie
    0.39
     Rie
    0.38
    dió
    0.38
     مرد
    0.37
     مرا
    0.37
     CNS
    0.36
     NIE
    0.36
    액
    0.36
     può
    0.36
     décor
    0.36
    Act Density 0.000%

    No Known Activations