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

    Neuronpedia

    INDEX
    Explanations

    four

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그리고
    0.39
    },-\
    0.39
    0.38
    สอง
    0.38
    ereur
    0.38
     অপর্ণ
    0.36
    ंदरे
    0.36
     Artur
    0.36
    そして
    0.36
    股权
    0.35
    POSITIVE LOGITS
    4
    0.66
    0.49
     cuatro
    0.45
     four
    0.41
     ۴
    0.41
     quatro
    0.41
    ４
    0.41
    four
    0.40
     ನಾಲ್
    0.40
     നാല
    0.39
    Act Density 0.017%

    No Known Activations