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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இல
    0.71
    รายการ
    0.68
    überkü
    0.67
    ક્ટર
    0.67
    上下
    0.65
    上市公司
    0.62
     Upl
    0.62
    scn
    0.61
    ibb
    0.61
    YN
    0.60
    POSITIVE LOGITS
     योग्यता
    0.74
     strategia
    0.73
     estratégia
    0.69
     جز
    0.67
     करना
    0.66
    ーブ
    0.66
     येत
    0.66
    вере
    0.65
     Canton
    0.65
     Garantie
    0.64
    Act Density 0.001%

    No Known Activations