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

    Neuronpedia

    INDEX
    Explanations

    emojis and positive expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.71
    ,
    0.71
     process
    0.69
    ,"
    0.63
     properties
    0.60
    ,”
    0.59
     constraints
    0.57
    ितीय
    0.57
     (@
    0.56
     MAT
    0.56
    POSITIVE LOGITS
    😃
    0.81
    emoji
    0.80
     ganó
    0.74
    😚
    0.74
     emoticon
    0.73
     ㅎ
    0.72
     근데
    0.72
    😁
    0.72
    😀
    0.72
     sonrisa
    0.72
    Act Density 0.093%

    No Known Activations