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

    Neuronpedia

    INDEX
    Explanations

    names and relevant biographical details of individuals

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

    Punctuation in legal or numerical contexts

    np_acts-logits-general · gemini-2.0-flash

    passing away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.48
     незавершена
    -0.47
     հղումներ
    -0.44
     Leistung
    -0.43
     autorytatywna
    -0.43
     Wikimedijinoj
    -0.40
    erapa
    -0.40
     فريبيس
    -0.40
     internetowa
    -0.38
     Meksiku
    -0.38
    POSITIVE LOGITS
     died
    0.66
     passed
    0.61
     Passed
    0.60
     formerly
    0.57
    transQ
    0.55
     peacefully
    0.54
    extAlignment
    0.50
     døde
    0.49
     beloved
    0.48
    Passed
    0.48
    Act Density 0.078%

    No Known Activations