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

    Neuronpedia

    INDEX
    Explanations

    book titles and authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     promotional
    0.45
     realtor
    0.44
     tailgate
    0.42
     داخلی
    0.42
     vidéo
    0.41
     hosted
    0.41
     leftover
    0.41
     rental
    0.41
     emailing
    0.41
     tiges
    0.40
    POSITIVE LOGITS
     selfishness
    0.56
     consciência
    0.51
     pikiran
    0.47
     sufrimiento
    0.46
     immortality
    0.45
    chapter
    0.44
     동물
    0.43
     ഞാൻ
    0.43
     Chapter
    0.43
     Auschwitz
    0.43
    Act Density 0.006%

    No Known Activations