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

    Neuronpedia

    INDEX
    Explanations

    URLs and web links in text

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

    web URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.46
     pleaſure
    -0.43
     createSlice
    -0.43
     Houſe
    -0.43
     ModelExpression
    -0.40
    <?
    -0.39
     Füßen
    -0.39
     disambiguazione
    -0.38
    Filmographie
    -0.38
     Garantía
    -0.37
    POSITIVE LOGITS
     URL
    0.60
     web
    0.58
    https
    0.56
     URLs
    0.56
     https
    0.55
     website
    0.53
     HTTPS
    0.53
    AddHtmlAttribute
    0.52
    http
    0.52
     url
    0.52
    Act Density 0.029%

    No Known Activations