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

    Neuronpedia

    INDEX
    Explanations

    proper names and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     என்கிறார்
    0.62
    त्या
    0.61
    จึง
    0.60
    即可
    0.60
    த்தும்
    0.60
    页面存档备份
    0.59
    ꯁ
    0.59
     subsequent
    0.58
     thereby
    0.56
    сят
    0.55
    POSITIVE LOGITS
    ,</
    1.41
     👋
    1.40
     спасибо
    1.36
     please
    1.32
     আপনি
    1.31
     你
    1.26
     youre
    1.26
    please
    1.25
     você
    1.24
     Öncelikle
    1.21
    Act Density 0.124%

    No Known Activations