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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that suggest the process of receiving or gathering information

    oai_token-act-pair · gemini-2.0-flash

    the word "as" in multiple languages

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

    "as" in multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -0.62
    AndEndTag
    -0.59
     AssemblyCompany
    -0.59
     NSCoder
    -0.57
     disambiguazione
    -0.57
     ujednoznacz
    -0.56
    الإنجليزية
    -0.56
    SourceChecksum
    -0.56
    XmlAccessorType
    -0.56
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     as
    2.70
     sebagai
    1.45
    as
    1.41
     как
    1.35
    作为
    1.15
     cât
    1.13
    sebagai
    1.12
     As
    1.11
     као
    1.09
     sebag
    1.09
    Act Density 2.441%

    No Known Activations