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

    Neuronpedia

    INDEX
    Explanations

    second-person and first-person pronouns

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

    tell us that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gare
    -0.46
    jScrollPane
    -0.40
     arşivlendi
    -0.40
     mismatch
    -0.39
     scraper
    -0.39
     pseud
    -0.39
     Bioaccumulative
    -0.39
     ChromeDriver
    -0.38
    SqlSession
    -0.38
    Mutagenicity
    -0.38
    POSITIVE LOGITS
     vertellen
    0.69
     know
    0.64
     kysy
    0.63
    know
    0.62
    Know
    0.60
     tell
    0.60
    say
    0.60
     řek
    0.59
     kertoo
    0.59
     erzählen
    0.58
    Act Density 0.013%

    No Known Activations