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

    Neuronpedia

    INDEX
    Explanations

    priority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    揣
    0.39
     Waldo
    0.37
     indu
    0.37
    怡
    0.37
    affold
    0.36
     threx
    0.36
     پلی
    0.35
    散
    0.34
     pyplot
    0.34
    chine
    0.34
    POSITIVE LOGITS
     priority
    2.81
    優先
    2.70
     приорите
    2.64
    priority
    2.58
    Priority
    2.56
     Priority
    2.53
     priorit
    2.41
    优先
    2.39
     prioridad
    2.39
    优先级
    2.39
    Act Density 0.032%

    No Known Activations