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

    Neuronpedia

    INDEX
    Explanations

    foreign language names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحالة
    0.48
     dependence
    0.44
    jmp
    0.42
    depends
    0.41
    Flicky
    0.41
     depending
    0.41
     situational
    0.40
     libc
    0.40
     പിന്ന
    0.40
     emphatic
    0.40
    POSITIVE LOGITS
    ຂອງ
    0.45
    ла
    0.44
    ுடன்
    0.42
     nuevas
    0.41
    一个月
    0.40
    ு
    0.40
    ர்களுக்கு
    0.39
    नए
    0.39
    ραν
    0.39
     nuevos
    0.39
    Act Density 0.006%

    No Known Activations