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

    Neuronpedia

    INDEX
    Explanations

    my prefix and Florida

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਦ
    0.37
    kerk
    0.36
    💨
    0.36
     ग़
    0.35
    }\
    0.34
    ಿಯು
    0.34
    される
    0.34
     більш
    0.34
     MONTH
    0.33
    された
    0.33
    POSITIVE LOGITS
     Лей
    0.40
    myTransform
    0.40
     indispensable
    0.39
    myLabels
    0.39
     Myl
    0.39
     मेरे
    0.39
     Fergus
    0.39
    说法
    0.38
     myof
    0.38
     My
    0.38
    Act Density 0.038%

    No Known Activations