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

    Neuronpedia

    INDEX
    Explanations

    guid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Não
    -0.08
    新业态
    -0.07
     super
    -0.07
     essen
    -0.07
     entirety
    -0.07
    あたり
    -0.07
    Australian
    -0.07
    Msg
    -0.07
     Wyoming
    -0.07
     cuda
    -0.07
    POSITIVE LOGITS
    網頁
    0.07
    معاي
    0.07
    .sep
    0.07
    珷
    0.07
    nova
    0.06
    меча
    0.06
     durable
    0.06
    🌑
    0.06
    работать
    0.06
     Çünkü
    0.06
    Act Density 0.001%

    No Known Activations