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

    Neuronpedia

    INDEX
    Explanations

    Three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governor
    -0.10
     braking
    -0.08
    Xe
    -0.08
    ignty
    -0.08
    縄
    -0.08
     righteousness
    -0.08
     Felix
    -0.08
     freeway
    -0.08
     educação
    -0.08
    xes
    -0.08
    POSITIVE LOGITS
     للبيع
    0.10
    打造
    0.09
     packaging
    0.09
     предусмотр
    0.09
    尺寸
    0.08
     упаков
    0.08
    👍
    0.08
     ofrecemos
    0.08
     hardcover
    0.08
     출시
    0.08
    Act Density 0.009%

    No Known Activations