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

    Neuronpedia

    INDEX
    Explanations

    gifts and presents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :=
    0.45
    }%
    0.44
     contaminating
    0.42
     disinformation
    0.42
     hydroxide
    0.41
    CRIPTOR
    0.40
    fusc
    0.40
     paradoxical
    0.39
    ahydro
    0.39
     സമര
    0.39
    POSITIVE LOGITS
     gift
    1.93
     gifts
    1.81
     regalos
    1.77
     подар
    1.77
     선물
    1.66
    礼物
    1.66
     cadeaux
    1.65
     подарок
    1.64
     Gift
    1.62
     Gifts
    1.61
    Act Density 0.055%

    No Known Activations