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

    Neuronpedia

    INDEX
    Explanations

    counting parts of sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    D
    0.44
     ချ
    0.43
    lü
    0.39
     anything
    0.35
    এমন
    0.35
    hluk
    0.34
     keď
    0.34
    Swan
    0.33
     mọi
    0.33
     jeśli
    0.33
    POSITIVE LOGITS
     davon
    1.09
     ervan
    1.05
     diantaranya
    0.98
     thereof
    0.98
     منهم
    0.84
     منها
    0.83
    其中的
    0.82
     dintre
    0.79
    其中
    0.77
     deles
    0.76
    Act Density 0.012%

    No Known Activations