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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or lack of specificity

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

    Following "not", "any", "specific", or negation words

    np_acts-logits-general · gemini-2.0-flash

    specific definition or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.34
     ніж
    -0.34
    ご理解
    -0.32
    出版年
    -0.31
     gepubliceerd
    -0.31
    Ox
    -0.31
    apache
    -0.31
    openConnection
    -0.30
    ische
    -0.30
     República
    -0.30
    POSITIVE LOGITS
     فريبيس
    0.70
    +#+#
    0.65
    StoryboardSegue
    0.60
     actual
    0.58
     незавершена
    0.54
     tartalomajánló
    0.54
    RefNanny
    0.54
     själva
    0.50
     Мексичка
    0.50
     وتسجيلات
    0.50
    Act Density 0.676%

    No Known Activations