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

    Neuronpedia

    INDEX
    Explanations

    well, as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻅ
    0.57
    ﺩ
    0.46
    OLUTION
    0.44
    IGHT
    0.43
    ﻁ
    0.42
    ÇÃO
    0.42
    イ
    0.42
    ÔNG
    0.41
    ﺃ
    0.40
    OLYBDENUM
    0.40
    POSITIVE LOGITS
    but
    0.47
     wodurch
    0.45
    ul
    0.43
     насколько
    0.42
    to
    0.41
     struts
    0.41
     anecdotes
    0.41
     जबकि
    0.40
     berichten
    0.40
    কিন্তু
    0.39
    Act Density 0.012%

    No Known Activations