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

    Neuronpedia

    INDEX
    Explanations

    next cumulative order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     સમજ
    0.42
    面倒
    0.41
    一手
    0.40
    つま
    0.40
    文化
    0.39
     trouv
    0.39
    Prz
    0.38
    enture
    0.38
     문화
    0.37
    鱔
    0.37
    POSITIVE LOGITS
     AGAIN
    0.68
     previous
    0.64
     cumulative
    0.60
     cumul
    0.59
     очередной
    0.59
     আগেও
    0.58
     ninth
    0.57
    Cumulative
    0.56
    cumulative
    0.55
     ANOTHER
    0.55
    Act Density 0.053%

    No Known Activations