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

    Neuronpedia

    INDEX
    Explanations

    various languages example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.52
    our
    0.50
     boundless
    0.47
     central
    0.46
    central
    0.45
     our
    0.43
     Central
    0.43
     to
    0.42
     oft
    0.42
     at
    0.42
    POSITIVE LOGITS
    篇文章
    0.49
    家伙
    0.47
    情况
    0.47
     фак
    0.46
    例子
    0.44
     شخص
    0.43
    數據
    0.43
     પ્રકાર
    0.43
    日子
    0.43
    říklad
    0.42
    Act Density 0.038%

    No Known Activations