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

    Neuronpedia

    INDEX
    Explanations

    known for or as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كتاب
    1.05
    。</
    1.04
    0.99
     أبي
    0.97
     كوب
    0.97
    。）
    0.95
    。[
    0.93
     مؤرشف
    0.92
     كار
    0.91
     сиг
    0.90
    POSITIVE LOGITS
     known
    1.27
    ა
    1.24
    स
    1.19
    ले
    1.13
    의
    1.07
     by
    1.06
    ה
    1.05
    et
    1.02
    ;
    1.02
    스
    1.00
    Act Density 0.041%

    No Known Activations