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

    Neuronpedia

    INDEX
    Explanations

    the abbreviation "etc." appearing after lists of items

    oai_token-act-pair · gemini-2.0-flash

    the term "etc." and related placeholders

    np_token-act-pair-logits · gpt-4o-mini

    etc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </tfoot>
    -0.55
     "..\..\..\
    -0.51
    oa̍t
    -0.51
     Maladies
    -0.51
    ochond
    -0.50
     Dam
    -0.48
     ElementRef
    -0.48
    kháu
    -0.48
    تج
    -0.47
    getWriter
    -0.47
    POSITIVE LOGITS
     متعلقه
    0.96
     ویکی‌پدیای
    0.85
    abestanden
    0.63
    ConstraintMaker
    0.60
     فريبيس
    0.58
    żli
    0.58
    脚注の使い方
    0.58
    encodeWith
    0.57
    EndProject
    0.56
    contentLoaded
    0.55
    Act Density 1.789%

    No Known Activations