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

    Neuronpedia

    INDEX
    Explanations

    high activation patterns indicating significant error handling or exceptional cases in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after a conditional statement

    np_acts-logits-general · gemini-2.0-flash

    foreign words and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.71
    resave
    -0.69
     Waray
    -0.69
     насељу
    -0.67
    IUrlHelper
    -0.67
    Personendaten
    -0.63
    tagHelperRunner
    -0.62
     propOrder
    -0.61
     AssemblyVersion
    -0.61
    цездатний
    -0.57
    POSITIVE LOGITS
     toutefois
    0.59
    vény
    0.57
     paroisse
    0.56
     AssemblyProduct
    0.56
    يميديا
    0.52
     cependant
    0.50
    omalainen
    0.50
    Advertisement
    0.50
    uttavia
    0.50
     förra
    0.50
    Act Density 0.038%

    No Known Activations