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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redirectTo
    0.41
     توصیه
    0.39
     proposes
    0.38
     خواست
    0.38
     emprend
    0.38
    allenge
    0.38
     SCRI
    0.38
     ধারণা
    0.38
    を通じて
    0.38
     nguyện
    0.38
    POSITIVE LOGITS
    sections
    0.44
     všetky
    0.44
     wszystkie
    0.44
     unimportant
    0.43
     например
    0.42
     minut
    0.42
    整個
    0.41
    f
    0.41
    整个
    0.40
    1
    0.40
    Act Density 0.092%

    No Known Activations