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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical notations or symbols

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

    legal citations and non-english articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.48
     Ful
    -0.40
    tvguidetime
    -0.40
     rozum
    -0.38
    請繼續往下閱讀
    -0.38
    oblig
    -0.36
    cửa
    -0.36
    remp
    -0.36
    urance
    -0.35
     NavController
    -0.35
    POSITIVE LOGITS
    تقاوى
    0.61
    Personendaten
    0.59
     Administrativna
    0.59
     ویکی‌پدی
    0.54
     člá
    0.54
    ThroughAttribute
    0.54
     article
    0.52
     CreateTagHelper
    0.50
     мәкал
    0.50
     Wikimedijinoj
    0.49
    Act Density 0.007%

    No Known Activations