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

    Neuronpedia

    INDEX
    Explanations

    struct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뽀
    -0.08
    报名
    -0.07
     ?
    -0.07
     person
    -0.07
     "+
    -0.07
     SOS
    -0.07
     Berm
    -0.07
    _days
    -0.06
    /no
    -0.06
    Side
    -0.06
    POSITIVE LOGITS
     Yapı
    0.08
    薄膜
    0.07
    עריכת
    0.07
    ㈼
    0.07
     grading
    0.07
    精密
    0.07
     membranes
    0.07
    柃
    0.07
    就行
    0.06
    omap
    0.06
    Act Density 0.004%

    No Known Activations