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

    Neuronpedia

    INDEX
    Explanations

    tables summarizing data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     постанов
    0.61
    鸾
    0.60
     keyword
    0.57
     राउत
    0.56
     slug
    0.56
     canonical
    0.56
    脇
    0.55
    aldb
    0.55
    0.53
     উদ্দেশ্যে
    0.52
    POSITIVE LOGITS
    تماد
    0.77
    )/\
    0.74
     المرس
    0.74
    䋇
    0.72
    鎬
    0.69
    :‏
    0.67
     거죠
    0.67
    ॰ऍ
    0.67
    ceğine
    0.66
    ㅀ
    0.65
    Act Density 0.011%

    No Known Activations