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

    Neuronpedia

    INDEX
    Explanations

    U

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سور
    -0.08
    His
    -0.08
    调动
    -0.07
    人数
    -0.07
     its
    -0.07
    James
    -0.07
     أيام
    -0.07
    loe
    -0.07
     khí
    -0.07
    _oid
    -0.07
    POSITIVE LOGITS
    extracomment
    0.08
    _REUSE
    0.07
     Kü
    0.07
    秦皇岛
    0.07
    汕头
    0.07
    �
    0.07
     każ
    0.07
    ㊨
    0.07
    Rad
    0.06
     graduates
    0.06
    Act Density 0.029%

    No Known Activations