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

    Neuronpedia

    INDEX
    Explanations

    as (multiple languages)

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mnopqr
    0.67
     થઇ
    0.66
     शीघ्र
    0.66
    把
    0.65
    ഹു
    0.63
    भिन्न
    0.63
    ępu
    0.62
     매우
    0.61
    อนุ
    0.61
    irable
    0.60
    POSITIVE LOGITS
     as
    3.08
     sebagai
    2.12
     As
    2.05
    作为
    1.93
    As
    1.93
     作为
    1.76
     jako
    1.66
     kao
    1.66
     Sebagai
    1.64
     као
    1.61
    Act Density 0.138%

    No Known Activations