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

    Neuronpedia

    INDEX
    Explanations

    farewells

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _detalle
    -0.07
    stice
    -0.07
    _once
    -0.07
    )==
    -0.07
     Москов
    -0.07
    uire
    -0.07
    也正是
    -0.07
     ){
    -0.06
    老龄化
    -0.06
    海岛
    -0.06
    POSITIVE LOGITS
    刘
    0.08
     Lu
    0.08
     ideas
    0.07
     poc
    0.07
    rl
    0.07
     desirable
    0.07
     Appears
    0.06
     Emotional
    0.06
     רבה
    0.06
    рам
    0.06
    Act Density 0.031%

    No Known Activations