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

    Neuronpedia

    INDEX
    Explanations

    styles, tones, and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certos
    0.43
     bestimmten
    0.41
     verlei
    0.40
     Utama
    0.40
     besonder
    0.39
    ̣n
    0.39
     erity
    0.39
     zusätzliche
    0.38
     besondere
    0.38
     certain
    0.37
    POSITIVE LOGITS
     ranging
    1.40
    ranging
    1.09
     ranged
    0.87
    from
    0.74
     from
    0.74
     от
    0.73
     диапазо
    0.73
     range
    0.71
     från
    0.71
    从
    0.71
    Act Density 0.177%

    No Known Activations