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

    Neuronpedia

    INDEX
    Explanations

    positive emotions and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ства
    1.21
    orsement
    1.20
    له
    1.19
    色列
    1.13
    ate
    1.10
     pembahasan
    1.09
    ર
    1.07
    oretically
    1.05
    ction
    1.04
    ️
    1.03
    POSITIVE LOGITS
     tuoi
    1.38
     felicidad
    1.36
     smacked
    1.32
     feliz
    1.30
     endings
    1.30
    ေါ
    1.28
    uiDesigner
    1.26
     Camper
    1.25
    kek
    1.23
    快樂
    1.21
    Act Density 0.023%

    No Known Activations