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

    Neuronpedia

    INDEX
    Explanations

    we can / we are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如图
    0.41
    交通事故
    0.40
    ydı
    0.39
    อบคุณ
    0.38
     compensated
    0.38
     circulatory
    0.37
    ണ്ഡ
    0.37
    ެ
    0.37
     }}(\
    0.37
     annuity
    0.37
    POSITIVE LOGITS
     shines
    0.44
     Novos
    0.42
     수
    0.39
    ?!"
    0.39
     creates
    0.39
     embodies
    0.38
     Qu
    0.37
     nouvelles
    0.37
     Necess
    0.37
     będ
    0.37
    Act Density 0.001%

    No Known Activations