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

    Neuronpedia

    INDEX
    Explanations

    if n <= 0 or n <= 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ไม่ได้
    0.40
     สา
    0.39
    ፈለ
    0.39
     कही
    0.38
    ฟ
    0.38
    Sorter
    0.38
    ibalsan
    0.38
    fwlink
    0.38
     టిప్పు
    0.38
    ksz
    0.38
    POSITIVE LOGITS
    这两个
    0.45
    这两
    0.43
     rabbits
    0.42
     FIB
    0.42
     Kedua
    0.42
     artistic
    0.41
     inilah
    0.41
     fibr
    0.41
     termin
    0.41
     rabbit
    0.41
    Act Density 0.114%

    No Known Activations