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

    Neuronpedia

    INDEX
    Explanations

    x, X, XL, ex variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bell
    0.98
    낯
    0.95
    อีก
    0.91
     Schild
    0.82
    まま
    0.82
     su
    0.81
     пона
    0.81
    őd
    0.80
    并发
    0.78
     Battista
    0.75
    POSITIVE LOGITS
    NUMX
    1.82
    treme
    1.39
    oxo
    1.30
    cellent
    1.30
    ʷ
    1.25
    ڽ
    1.23
     maxX
    1.23
    xxxxxxxx
    1.19
    posure
    1.16
    avier
    1.16
    Act Density 0.574%

    No Known Activations