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

    Neuronpedia

    INDEX
    Explanations

    | she | vic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beserta
    0.50
     başlı
    0.41
    onacci
    0.39
     นั่น
    0.39
     rồi
    0.38
    ān
    0.38
    elerini
    0.38
     然后
    0.38
     কিংবা
    0.38
     แล้ว
    0.38
    POSITIVE LOGITS
     lacks
    0.50
     lacked
    0.47
     lack
    0.44
     occasional
    0.41
     noticeable
    0.41
    缺乏
    0.41
     niektórych
    0.41
     interestingly
    0.41
     أيضا
    0.40
     cenderung
    0.40
    Act Density 0.205%

    No Known Activations