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

    Neuronpedia

    INDEX
    Explanations

    iPhone, text, or single

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ayl
    0.42
     landfall
    0.41
    ጅም
    0.40
     revenue
    0.39
     районов
    0.38
     pitches
    0.37
     отрасли
    0.37
     매출
    0.37
    jectory
    0.36
     ውጤ
    0.36
    POSITIVE LOGITS
    ^{
    0.49
     bepaalde
    0.49
     følgende
    0.47
    某些
    0.46
     bestimmte
    0.45
    下記
    0.43
    ಗಳಲ್ಲಿ
    0.43
    的一些
    0.43
     bestimmten
    0.42
    認為
    0.42
    Act Density 0.006%

    No Known Activations