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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     educativas
    0.28
     உலகம்
    0.27
     entrenador
    0.26
     खोल
    0.26
    广
    0.26
     nombreuses
    0.26
     asalamualaikum
    0.26
     nourrice
    0.26
     භාවිතා
    0.26
     аккумулятор
    0.26
    POSITIVE LOGITS
     of
    0.41
    0
    0.41
    +
    0.35
    <0x80>
    0.35
     or
    0.31
    %
    0.31
    -
    0.30
    za
    0.29
    _
    0.28
     and
    0.27
    Act Density 0.359%

    No Known Activations