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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or contradiction in statements

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

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     textes
    -0.36
    psfrag
    -0.34
     prépar
    -0.33
    記事
    -0.33
     sauve
    -0.33
     retrô
    -0.32
     zprá
    -0.32
     アクリル
    -0.32
    thoughts
    -0.32
     mal
    -0.32
    POSITIVE LOGITS
     مشين
    0.75
     kasarigan
    0.70
    AutoScaleMode
    0.65
    ItemBackground
    0.64
    GEBURTSDATUM
    0.62
     Италијани
    0.59
    ंदीखरीदारी
    0.59
    0.58
     ویکی‌پدی
    0.57
    windowFixed
    0.54
    Act Density 0.109%

    No Known Activations