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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ання
    -0.06
    اب
    -0.06
    ères
    -0.06
    킬
    -0.06
     imposes
    -0.06
     userID
    -0.06
    ُس
    -0.06
    コード
    -0.06
    اف
    -0.06
    ограф
    -0.06
    POSITIVE LOGITS
     рекоменда
    0.07
     нас
    0.07
    rx
    0.07
     Liver
    0.07
     Coronavirus
    0.06
    Password
    0.06
     nationalist
    0.06
    ()}}↵
    0.06
    Cancelar
    0.06
    ória
    0.06
    Act Density 0.042%

    No Known Activations