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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or causation

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

    to establish a purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.84
    richTextPanel
    -0.77
     Biôgrafia
    -0.73
     nahilalakip
    -0.71
    WebElementEntity
    -0.71
    LookAnd
    -0.71
    windowFixed
    -0.70
     препратки
    -0.70
     propOrder
    -0.69
     autorytatywna
    -0.68
    POSITIVE LOGITS
    Eins
    0.31
     prove
    0.31
    肥
    0.30
     map
    0.28
     التف
    0.28
     để
    0.28
     års
    0.28
     proves
    0.28
    ナツ
    0.28
     prevent
    0.27
    Act Density 0.136%

    No Known Activations