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

    Neuronpedia

    INDEX
    Explanations

    either or both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ایسے
    0.44
     افرادی
    0.41
     ऐसी
    0.40
    ೫
    0.40
    those
    0.40
    Such
    0.39
     Those
    0.39
     এমন
    0.38
    នូវ
    0.38
     Such
    0.38
    POSITIVE LOGITS
     either
    0.61
     otherwise
    0.58
     conducive
    0.57
     hopefully
    0.57
     nevertheless
    0.55
     nonetheless
    0.53
     reminiscent
    0.53
     characteristic
    0.52
     deemed
    0.50
     both
    0.47
    Act Density 0.072%

    No Known Activations