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

    Neuronpedia

    INDEX
    Explanations

    descriptive manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     સારું
    0.48
     iyi
    0.44
    ങ്ങ്
    0.43
     ভাল
    0.42
     مفید
    0.42
     полез
    0.41
     interesting
    0.40
     intéressante
    0.40
     bepaalde
    0.40
     спокойно
    0.40
    POSITIVE LOGITS
    且
    0.69
     للغاية
    0.69
     throughout
    0.68
    ly
    0.64
    并且
    0.63
     despite
    0.63
     enough
    0.62
     allowing
    0.61
     according
    0.60
     and
    0.59
    Act Density 0.624%

    No Known Activations