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

    Neuronpedia

    INDEX
    Explanations

    capitalized words often used in model names

    oai_token-act-pair · gemini-2.0-flash

    terms related to Peugeot and navigation

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

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.73
    ViewImports
    -0.71
    ритори
    -0.67
     disambiguazione
    -0.66
    Portale
    -0.65
    tagHelperRunner
    -0.63
     autorytatywna
    -0.63
    хьтан
    -0.63
    elemField
    -0.62
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
    ThroughAttribute
    0.45
    hen
    0.45
    LL
    0.43
    Kaynakça
    0.43
    وف
    0.42
    可
    0.41
    HC
    0.41
    pev
    0.41
    com
    0.40
    ko
    0.40
    Act Density 0.023%

    No Known Activations