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

    Neuronpedia

    INDEX
    Explanations

    dialogue ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     😉
    1.52
     :).
    1.49
     nhỉ
    1.40
     🙂
    1.34
     ;)
    1.32
     :)
    1.30
     :-)
    1.28
     ;-)
    1.26
     😊
    1.18
     =)
    1.16
    POSITIVE LOGITS
    !;
    0.86
    我要
    0.85
    နှင့်
    0.72
    ！”
    0.71
    !--
    0.70
    !\
    0.70
    !,
    0.70
     พร้อม
    0.69
    публи
    0.67
    yser
    0.67
    Act Density 0.039%

    No Known Activations