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

    Neuronpedia

    INDEX
    Explanations

    permission to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ॔
    0.50
    สามารถ
    0.50
    Можно
    0.45
     بتوان
    0.44
    surgical
    0.44
    يمكن
    0.44
     можна
    0.43
     Fäh
    0.43
    可以用
    0.42
    可以将
    0.41
    POSITIVE LOGITS
     into
    0.54
    into
    0.54
     access
    0.52
     ample
    0.52
     доступа
    0.52
     допуска
    0.49
     اجازه
    0.49
     Zugang
    0.48
     onto
    0.48
     allowance
    0.47
    Act Density 0.007%

    No Known Activations