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

    Neuronpedia

    INDEX
    Explanations

    How many start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    為了
    0.46
    เพื่อให้
    0.45
     为了
    0.44
     כדי
    0.44
    为了
    0.43
     impacto
    0.43
    잖아요
    0.43
    Чтобы
    0.42
     bertujuan
    0.42
     اہمیت
    0.42
    POSITIVE LOGITS
     begins
    0.51
     three
    0.49
     four
    0.46
     starts
    0.45
     начать
    0.45
     пять
    0.44
     five
    0.44
     beginnt
    0.44
     具体
    0.44
     çeşitli
    0.43
    Act Density 0.035%

    No Known Activations