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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or words indicating negation

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

    ne, no, none, não, not, n't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.52
    subpackage
    -0.51
    Бахар
    -0.48
    OpenHelper
    -0.47
    SuspendLayout
    -0.45
    مصادر
    -0.43
    Сылтамалар
    -0.42
    DoubleQuotes
    -0.40
     ExecuteAsync
    -0.40
    IRQn
    -0.40
    POSITIVE LOGITS
     never
    0.53
     cannot
    0.51
    twimg
    0.47
     onBind
    0.46
    ambién
    0.46
    ihnach
    0.43
     नहीं
    0.42
     δεν
    0.42
     cilia
    0.42
     really
    0.41
    Act Density 0.009%

    No Known Activations