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

    Neuronpedia

    INDEX
    Explanations

    phrases with coordinating conjunctions such as "and" or "or" used multiple times to indicate complex relationships or lists

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.90
    AutoScaleMode
    -0.89
    LookAnd
    -0.68
    QMetaType
    -0.66
     ویکی‌پدی
    -0.65
    OGND
    -0.64
     мәкал
    -0.62
     TextInputType
    -0.62
    postsleuth
    -0.61
    antası
    -0.60
    POSITIVE LOGITS
     another
    0.76
     seven
    0.67
     five
    0.67
     approximately
    0.67
     
    0.66
     eight
    0.66
     nine
    0.62
     six
    0.62
     nearly
    0.61
     £
    0.60
    Act Density 0.107%

    No Known Activations