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

    Neuronpedia

    INDEX
    Explanations

    popularity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    1.46
    ח
    1.39
    נ
    1.34
    ال
    1.29
    قد
    1.26
    在
    1.23
    ح
    1.21
    一
    1.17
    مس
    1.12
    ל
    1.11
    POSITIVE LOGITS
    혔
    1.13
    вання
    1.02
     the
    0.92
     জনপ্রিয়তা
    0.91
    지
    0.91
     populer
    0.88
    으며
    0.87
     mainstay
    0.86
    ած
    0.85
    지요
    0.84
    Act Density 0.039%

    No Known Activations