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

    Neuronpedia

    INDEX
    Explanations

    power of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谲
    0.40
    مان
    0.39
     Dạ
    0.38
    TaskManager
    0.37
    lans
    0.37
    售价
    0.37
    sächlich
    0.37
     werk
    0.36
     Wyman
    0.36
    GoString
    0.36
    POSITIVE LOGITS
     –
    0.46
     ६
    0.46
     военно
    0.42
     ->
    0.41
     १८
    0.41
     -->
    0.39
     Peral
    0.39
     ­
    0.39
    たない
    0.39
    gada
    0.38
    Act Density 0.009%

    No Known Activations