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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns for royalty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hang
    0.60
     ivory
    0.57
    rologist
    0.56
    loem
    0.56
     onions
    0.56
    indrical
    0.55
     dau
    0.54
    imbledon
    0.53
     фигу
    0.53
    ണ്ടു
    0.53
    POSITIVE LOGITS
     His
    3.59
    His
    3.35
     Her
    3.12
    Her
    2.92
     Его
    2.24
     HIS
    2.09
     Zijn
    2.06
    HIS
    2.00
     Himself
    1.94
     HER
    1.93
    Act Density 0.019%

    No Known Activations