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

    Neuronpedia

    INDEX
    Explanations

    enum class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ное
    0.39
     alrededor
    0.39
    崆
    0.37
     harm
    0.37
     एग्जामिनेशन
    0.36
    ˖
    0.36
    нце
    0.36
     बनती
    0.36
     विभागीय
    0.36
     воз
    0.36
    POSITIVE LOGITS
     class
    1.81
    class
    1.80
     класс
    1.18
     classe
    1.16
     clase
    1.13
     klasse
    1.02
     kelas
    0.97
    クラス
    0.95
     Class
    0.95
     Klasse
    0.94
    Act Density 0.020%

    No Known Activations