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

    Neuronpedia

    INDEX
    Explanations

    expressing thoughts/opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    情況
    -0.08
    _exam
    -0.07
    쉘
    -0.07
    websocket
    -0.07
    �
    -0.07
    เคล
    -0.07
    的概率
    -0.07
    aurants
    -0.07
    ًا
    -0.07
    (ca
    -0.07
    POSITIVE LOGITS
    统筹
    0.07
     Hol
    0.07
     estr
    0.06
    Israeli
    0.06
     Far
    0.06
     antivirus
    0.06
     Reserved
    0.06
    unction
    0.06
     Raphael
    0.06
    车
    0.06
    Act Density 0.166%

    No Known Activations