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

    Neuronpedia

    INDEX
    Explanations

    positive emotional responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存在
    0.69
    собенности
    0.66
    achery
    0.64
    طور
    0.64
    เปอร์
    0.63
     defaul
    0.63
     maturities
    0.62
    标识
    0.62
    φορά
    0.62
    ված
    0.61
    POSITIVE LOGITS
     smile
    1.52
     tears
    1.44
     goose
    1.41
     smiled
    1.39
     giddy
    1.37
     shudder
    1.36
     tremble
    1.35
     exhilar
    1.31
     chills
    1.29
     feeling
    1.28
    Act Density 0.136%

    No Known Activations