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

    Neuronpedia

    INDEX
    Explanations

    socket, code, lite, timestamp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    0.55
    ಮ
    0.54
    ત
    0.51
    事は
    0.48
    פים
    0.48
    ření
    0.47
    い
    0.47
    lichess
    0.47
    dzić
    0.47
    無料
    0.47
    POSITIVE LOGITS
    o
    0.57
     filtro
    0.50
     volatile
    0.49
     단순히
    0.47
     filter
    0.47
     settore
    0.45
     haircut
    0.45
     corpi
    0.45
     postup
    0.44
    older
    0.44
    Act Density 0.002%

    No Known Activations