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

    Neuronpedia

    INDEX
    Explanations

    punctuation-related features

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

    date of birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    archiviato
    -0.68
    ViewImports
    -0.67
     հղումներ
    -0.66
     дописавши
    -0.56
     оригіналу
    -0.54
    uxxxx
    -0.53
     فريبيس
    -0.52
    UrlResolution
    -0.52
     dAtA
    -0.51
     يتيمه
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    0.46
    Abit
    0.43
         
    0.39
     imperf
    0.38
    didSet
    0.36
    ATN
    0.36
     neceſſ
    0.36
    stackSize
    0.35
     irra
    0.35
     Mecca
    0.34
    Act Density 0.000%

    No Known Activations