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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conv
    -0.07
    'une
    -0.07
    @"
    -0.06
    {%
    -0.06
    Deep
    -0.06
     однов
    -0.06
    кат
    -0.06
    _True
    -0.06
    uellement
    -0.06
     플
    -0.06
    POSITIVE LOGITS
    世紀
    0.07
    ině
    0.07
     無
    0.06
    업체
    0.06
    <-
    0.06
    <ll
    0.06
    wang
    0.06
     vests
    0.06
     Whatsapp
    0.06
     Checkout
    0.06
    Act Density 0.271%

    No Known Activations