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

    Neuronpedia

    INDEX
    Explanations

    thế kỷ và thế giới

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ょう
    0.48
    ეც
    0.42
    phant
    0.41
    સે
    0.40
    emt
    0.40
    眙
    0.40
     sequ
    0.40
     immagine
    0.40
     semillas
    0.39
    fas
    0.39
    POSITIVE LOGITS
     Walden
    0.43
     kỷ
    0.40
    력
    0.39
    力の
    0.38
     Herbert
    0.37
     bound
    0.37
     Hệ
    0.36
     landslide
    0.36
     Abbreviations
    0.36
    AllWindows
    0.36
    Act Density 0.001%

    No Known Activations