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

    Neuronpedia

    INDEX
    Explanations

    aspectos clave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     która
    1.68
     kojoj
    1.66
     koju
    1.62
     която
    1.62
     ktorá
    1.59
     Its
    1.55
     яка
    1.55
     itself
    1.54
     its
    1.53
    Its
    1.52
    POSITIVE LOGITS
     kurie
    1.66
     kteří
    1.66
     الذين
    1.64
     kojima
    1.64
    ניים
    1.64
     którzy
    1.59
     которые
    1.59
     които
    1.58
     ktorí
    1.57
     якія
    1.54
    Act Density 0.222%

    No Known Activations