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

    Neuronpedia

    INDEX
    Explanations

    words expressing uncertainty or possibility

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

    indicating possibility or uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.62
     tématu
    -0.54
     autorytatywna
    -0.52
     initComponents
    -0.51
    SharedCtor
    -0.50
    DoubleQuotes
    -0.48
    ingtones
    -0.48
     BrowserModule
    -0.46
    URLException
    -0.45
     Wikimédia
    -0.45
    POSITIVE LOGITS
    maybe
    0.58
    Maybe
    0.53
     Maybe
    0.50
     maybe
    0.49
    perhaps
    0.48
     perhaps
    0.45
    ✭✭
    0.44
    possibly
    0.43
     possibly
    0.43
     Возможно
    0.43
    Act Density 0.020%

    No Known Activations