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

    Neuronpedia

    INDEX
    Explanations

    Marcus Aurelius

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acesta
    0.66
     এটি
    0.63
     koristiti
    0.60
     ይህ
    0.59
     tartan
    0.57
     guru
    0.57
     धरना
    0.56
     nieuw
    0.55
     تیل
    0.55
     grapefruit
    0.53
    POSITIVE LOGITS
     Closed
    0.50
    老年
    0.47
    MY
    0.46
    vam
    0.45
    fclose
    0.44
    años
    0.44
    debugging
    0.44
    के
    0.44
    航空
    0.44
    妺
    0.43
    Act Density 0.000%

    No Known Activations