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

    Neuronpedia

    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .basic
    -0.06
    lovak
    -0.06
    DD
    -0.06
    زر
    -0.06
     tanggal
    -0.06
    ök
    -0.06
     Slovak
    -0.06
    ui
    -0.06
     bénéfic
    -0.06
    docker
    -0.06
    POSITIVE LOGITS
    cart
    0.07
    罨
    0.07
     Anaheim
    0.07
     Assembly
    0.07
    網站
    0.07
     enact
    0.06
     |--------------------------------------------------------------------------↵
    0.06
    업체
    0.06
     nhạc
    0.06
    代言人
    0.06
    Act Density 0.004%

    No Known Activations