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

    Neuronpedia

    INDEX
    Explanations

    numbers, percentages, currency, rankings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inverted
    0.45
    Sheikh
    0.40
    眠
    0.40
    marquee
    0.39
    aden
    0.39
    primarily
    0.38
    occasion
    0.38
    Biden
    0.38
    decade
    0.38
    fin
    0.38
    POSITIVE LOGITS
     Vau
    0.44
     nosso
    0.43
     artisti
    0.43
     permitem
    0.43
     vilket
    0.42
     spé
    0.42
     permiten
    0.42
     serem
    0.42
     yazı
    0.41
     regler
    0.41
    Act Density 0.001%

    No Known Activations