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

    Neuronpedia

    INDEX
    Explanations

    eyes fixed on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arker
    0.57
     within
    0.55
     फांसी
    0.54
     ó
    0.53
    ภายใน
    0.53
    的一个
    0.51
    一丝
    0.51
    圴
    0.51
    成立于
    0.50
     אך
    0.50
    POSITIVE LOGITS
    4
    0.72
    يد
    0.70
    1
    0.68
     جديد
    0.63
     الدين
    0.61
    9
    0.59
    čina
    0.58
    0
    0.57
    يدات
    0.56
    RDD
    0.56
    Act Density 0.006%

    No Known Activations