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

    Neuronpedia

    INDEX
    Explanations

    shortlist

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Card
    -0.09
    undles
    -0.08
    bundles
    -0.07
    tet
    -0.07
    admins
    -0.07
    法庭
    -0.07
    몴
    -0.07
    UD
    -0.07
     Parameters
    -0.06
    lando
    -0.06
    POSITIVE LOGITS
     brig
    0.08
     выбрать
    0.07
    $results
    0.07
     وخ
    0.07
     trg
    0.07
    ผ
    0.07
     الفرص
    0.06
     Goose
    0.06
     biết
    0.06
    쒯
    0.06
    Act Density 0.041%

    No Known Activations