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

    Neuronpedia

    INDEX
    Explanations

    plugin names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gorge
    0.35
    磴
    0.34
    浾
    0.33
    说完
    0.33
     وړیا
    0.33
    MiddleCenter
    0.33
    wał
    0.32
    咊
    0.32
    <unused338>
    0.32
    Salmon
    0.32
    POSITIVE LOGITS
    ：
    0.71
    :
    0.70
    ៖
    0.50
    ：《
    0.47
    ::
    0.45
    :'
    0.44
    ➡
    0.43
    :&
    0.43
    ︰
    0.43
    ：“
    0.41
    Act Density 0.000%

    No Known Activations