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

    Neuronpedia

    INDEX
    Explanations

    the adjective "original" near nouns and scientific notation in research papers

    oai_token-act-pair · gemini-2.0-flash

    original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.55
     دریافت‌شده
    -0.53
     Staates
    -0.53
    #+#
    -0.53
     plow
    -0.51
     Sodom
    -0.50
    ofollow
    -0.49
     StatefulWidget
    -0.48
    tadır
    -0.48
     kasarigan
    -0.48
    POSITIVE LOGITS
    SuspendLayout
    0.61
    DeleteBehavior
    0.59
    Portail
    0.58
    Kjelder
    0.57
     يتيمه
    0.54
     InputDecoration
    0.50
     versa
    0.48
     intérieure
    0.48
    stanbul
    0.48
     disambiguazione
    0.47
    Act Density 1.504%

    No Known Activations