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

    Neuronpedia

    INDEX
    Explanations

    page numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ™,
    0.93
    ™.
    0.77
    isted
    0.76
     tremend
    0.76
    ®,
    0.75
     पढ़ेंः
    0.75
    ,[
    0.73
    ଷ୍
    0.72
     Reserve
    0.72
    ™
    0.72
    POSITIVE LOGITS
    รู้จัก
    0.73
    增加
    0.73
     লড়াই
    0.71
     နှစ်
    0.71
     تكتب
    0.71
     nap
    0.69
     Öncelikle
    0.66
     द्वि
    0.65
     specialize
    0.65
     Örneğin
    0.64
    Act Density 0.021%

    No Known Activations