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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document

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

    bibliographic references related to scientific journals

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.60
    addCriterion
    -0.54
    InvalidProtocol
    -0.53
     بتاريخ
    -0.53
    IonicModule
    -0.52
    ніципа
    -0.52
    tidaknya
    -0.51
    NameInMap
    -0.49
     betweenstory
    -0.48
    ItemBackground
    -0.48
    POSITIVE LOGITS
    OGND
    0.73
     Audiodateien
    0.61
    AndEndTag
    0.61
    xically
    0.58
    colhead
    0.57
    StackNavigator
    0.55
    Obrázky
    0.54
    rativo
    0.53
     cancels
    0.52
    oprecipitation
    0.51
    Act Density 0.015%

    No Known Activations