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

    Neuronpedia

    INDEX
    Explanations

    sorting and sorted data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मास्क
    0.43
    补贴
    0.42
     berlang
    0.41
    茸
    0.41
    ccnc
    0.41
    脱毛
    0.41
    streetlight
    0.40
     সানডে
    0.40
    பிலோ
    0.39
    保湿
    0.39
    POSITIVE LOGITS
     sorting
    2.28
     Sorting
    2.19
    Sorting
    2.13
     сорти
    1.98
     sorted
    1.96
    排序
    1.90
    sorting
    1.88
     Sorted
    1.73
    sorted
    1.73
     Sort
    1.71
    Act Density 0.098%

    No Known Activations