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

    Neuronpedia

    INDEX
    Explanations

    nth largest number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     그다음에
    0.52
    alertDialog
    0.47
    晝
    0.47
    ówczas
    0.46
    。。。
    0.45
     évén
    0.45
     FXMLLoader
    0.44
    arsipkan
    0.44
    。。
    0.44
     Chayin
    0.44
    POSITIVE LOGITS
     Exactly
    0.42
     गुस्सा
    0.41
     to
    0.40
     exactly
    0.39
     Tink
    0.38
     Sw
    0.37
    ;#
    0.37
     demanding
    0.37
     den
    0.37
     equipped
    0.37
    Act Density 0.420%

    No Known Activations