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

    Neuronpedia

    INDEX
    Explanations

    happy endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тые
    0.77
    0.74
     इंपोर्टेंट
    0.71
    明确
    0.71
     esempi
    0.71
    пуляр
    0.70
    ("",
    0.70
    例子
    0.69
    ದಿ
    0.67
     lastly
    0.67
    POSITIVE LOGITS
     😉
    2.30
     ;)
    2.29
     ;-)
    2.12
     :)
    1.99
     haha
    1.99
     😄
    1.96
     😁
    1.93
     hehe
    1.93
     hahaha
    1.92
     😊
    1.90
    Act Density 0.394%

    No Known Activations