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

    Neuronpedia

    INDEX
    Explanations

    introduces definitions or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰
    0.64
     egip
    0.52
    ’
    0.52
     camas
    0.50
     mịn
    0.48
    itabbam
    0.48
    頂いた
    0.48
     счастли
    0.47
     temporadas
    0.46
    이었
    0.46
    POSITIVE LOGITS
    ية
    0.60
    是
    0.59
    0.55
    ير
    0.54
     is
    0.47
     was
    0.46
    是我们
    0.45
     kamen
    0.45
    beelding
    0.44
    는
    0.44
    Act Density 1.376%

    No Known Activations