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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically those related to saints and geographic locations

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

    Saint names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteBarrier
    -0.42
    ulipas
    -0.42
    cookieParser
    -0.41
     guste
    -0.41
     gustaría
    -0.40
    AndEndTag
    -0.38
    Diweddarwch
    -0.37
    listdir
    -0.36
    Rptr
    -0.36
    蝉
    -0.36
    POSITIVE LOGITS
     Saint
    0.84
    Saint
    0.79
    Sainte
    0.78
     SAINT
    0.78
     saint
    0.70
     saints
    0.67
     Sainte
    0.66
     Saints
    0.65
     Sankt
    0.65
    saint
    0.63
    Act Density 0.027%

    No Known Activations