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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sach
    -0.08
     eaten
    -0.06
    �
    -0.06
    獲
    -0.06
    éru
    -0.06
    EDIATEK
    -0.06
     forwarding
    -0.06
     pazar
    -0.06
    赢
    -0.06
     через
    -0.06
    POSITIVE LOGITS
     complexity
    0.07
     irresist
    0.07
     stark
    0.07
     للد
    0.07
    ulture
    0.06
     віднов
    0.06
    َّ
    0.06
    ！');↵
    0.06
     requirement
    0.06
     восп
    0.06
    Act Density 0.188%

    No Known Activations