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

    Neuronpedia

    INDEX
    Explanations

    providing helpful responses or service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kyverno
    0.44
     الترب
    0.42
    事实上
    0.39
     रोटी
    0.39
    จะมี
    0.39
    icidal
    0.38
    甚至
    0.38
    IRONMENT
    0.38
    νονται
    0.38
    фектив
    0.37
    POSITIVE LOGITS
     customers
    0.40
    جميع
    0.40
     ط
    0.39
     رضا
    0.39
     customer
    0.38
    ਠ
    0.38
     every
    0.38
     وح
    0.38
     lasted
    0.38
    ਿ
    0.37
    Act Density 0.001%

    No Known Activations