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

    Neuronpedia

    INDEX
    Explanations

    percentages of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ettamente
    0.38
    права
    0.38
    essoa
    0.37
    endien
    0.36
    칫
    0.36
    邹
    0.35
    สอง
    0.35
    కున్నారు
    0.35
    ร้อม
    0.34
     حسین
    0.34
    POSITIVE LOGITS
     percent
    0.95
     procent
    0.79
     (%)
    0.77
     процентов
    0.76
     percentage
    0.76
    percent
    0.75
     (\%)
    0.71
     PERCENT
    0.70
     Prozent
    0.69
     $\%$
    0.69
    Act Density 0.034%

    No Known Activations