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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beg
    -0.07
    僵尸
    -0.07
     HAR
    -0.07
    uv
    -0.07
     acquired
    -0.07
     Xen
    -0.07
    坏
    -0.07
     GET
    -0.06
    trans
    -0.06
    hus
    -0.06
    POSITIVE LOGITS
    楝
    0.09
    았
    0.07
     לכן
    0.07
    �
    0.07
    incip
    0.07
     //////////////////////////////////////////////////////////////////////////
    0.07
    سف
    0.07
    自来
    0.07
    ಥ
    0.07
    مقا
    0.07
    Act Density 0.001%

    No Known Activations