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

    Neuronpedia

    INDEX
    Explanations

    emojis and faces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    稈
    0.44
    targetReference
    0.42
    ณฑ์
    0.42
    鏗
    0.41
     கட்டமை
    0.40
     الاساس
    0.40
    軼
    0.40
    㝅
    0.40
    LVANIA
    0.39
     principalTable
    0.38
    POSITIVE LOGITS
     emoji
    1.03
     emoticon
    0.98
     smiley
    0.97
    emoji
    0.90
     emojis
    0.87
    Emoji
    0.83
    smiley
    0.80
     wink
    0.75
     Emoji
    0.73
     smiling
    0.71
    Act Density 0.010%

    No Known Activations