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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and statistics

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

    Numbers within addresses, IDs, or codes

    np_acts-logits-general · gemini-2.0-flash

    numbers and address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.62
    }{*}{}
    -0.59
     للمعارف
    -0.57
    ￡
    -0.57
     poser
    -0.56
     themselves
    -0.54
     Onions
    -0.52
     Seul
    -0.52
    джан
    -0.49
    mability
    -0.49
    POSITIVE LOGITS
    帖最后由
    0.72
    WebElementEntity
    0.67
    SourceChecksum
    0.58
    lapsingToolbar
    0.58
    MessageTagHelper
    0.57
    windowFixed
    0.55
    UnusedPrivate
    0.53
    IndentedString
    0.52
    -"+
    0.52
     Lawson
    0.52
    Act Density 0.113%

    No Known Activations