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

    Neuronpedia

    INDEX
    Explanations

    numbers quantified by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.48
    ب
    1.24
    د
    1.18
    و
    1.11
    et
    1.10
     and
    1.08
    ಾ
    1.08
    ل
    1.03
    كا
    1.02
    e
    1.02
    POSITIVE LOGITS
    ৫
    0.78
     Diabetic
    0.75
     fifteen
    0.73
    .
    0.71
     ten
    0.69
    _
    0.68
     nineteen
    0.67
    OF
    0.66
     hundred
    0.66
     twelve
    0.66
    Act Density 0.048%

    No Known Activations