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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections

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

    "One of" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    phrases beginning 'one of the'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kaynakça
    -0.60
     ویکی‌پدیای
    -0.59
    Hochspringen
    -0.59
    Beweg
    -0.56
    PROV
    -0.55
    AutoresizingMask
    -0.53
    nościo
    -0.53
     createdAt
    -0.52
    -0.52
     Efq
    -0.52
    POSITIVE LOGITS
     للاسماء
    0.80
    Населення
    0.73
     CURIAM
    0.64
    hões
    0.58
    adaptiveStyles
    0.55
     favorite
    0.55
    Someday
    0.54
     eorum
    0.53
    ($__
    0.52
    UnusedPrivate
    0.52
    Act Density 0.108%

    No Known Activations