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

    Neuronpedia

    INDEX
    Explanations

    option 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ро
    1.29
    it
    1.22
    АС
    1.18
    ot
    1.11
    ยัง
    1.11
     և
    1.11
    em
    1.10
    or
    1.09
    ла
    1.09
    s
    1.08
    POSITIVE LOGITS
    speople
    1.54
    이면
    1.36
     enkelt
    1.35
    ಬ್ಬಿಣ
    1.27
     arbets
    1.24
    ۔۔
    1.23
     ойноо
    1.22
    我相信
    1.21
     devote
    1.18
    ます
    1.17
    Act Density 0.129%

    No Known Activations