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

    Neuronpedia

    INDEX
    Explanations

    foreign language terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंत
    0.44
    因
    0.43
    見
    0.43
    رت
    0.42
    最多
    0.40
    ب
    0.40
    ظم
    0.39
    بخ
    0.38
    رفت
    0.38
    بر
    0.38
    POSITIVE LOGITS
     дзяржа
    0.52
     നേതാ
    0.51
     теркәлү
    0.50
     lipos
    0.50
     അധികാര
    0.49
     tokamak
    0.48
     Спорттук
    0.48
     레드
    0.48
     phospholip
    0.47
     గౌ
    0.47
    Act Density 0.002%

    No Known Activations