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

    Neuronpedia

    INDEX
    Explanations

    collection of related items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hver
    0.48
     EACH
    0.47
    प्रत्य
    0.46
     svaki
    0.44
     mỗi
    0.44
     prácticamente
    0.42
     każdy
    0.42
     кожен
    0.41
     each
    0.41
    each
    0.41
    POSITIVE LOGITS
    一系列
    0.75
    若干
    0.68
    insieme
    0.67
    一群
    0.66
     مجموعة
    0.65
     набор
    0.64
     related
    0.62
     collection
    0.62
    相關
    0.62
    複数の
    0.61
    Act Density 0.034%

    No Known Activations