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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قبل
    -0.08
     이미
    -0.08
    粥
    -0.07
     báo
    -0.07
    Vertex
    -0.07
     apopt
    -0.07
    _func
    -0.07
     mongo
    -0.07
     soll
    -0.07
     בבוקר
    -0.07
    POSITIVE LOGITS
     Thần
    0.07
    _refs
    0.07
     */↵↵
    0.07
    ümüz
    0.06
     augmented
    0.06
    〼
    0.06
    傥
    0.06
    idences
    0.06
     recomm
    0.06
    第八
    0.06
    Act Density 0.000%

    No Known Activations