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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or strong belief

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

    expressing certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.49
     cafetería
    -0.48
     initComponents
    -0.47
     récents
    -0.46
     húmedo
    -0.43
    Eksterne
    -0.43
     Ayuda
    -0.42
    ImageField
    -0.41
     récentes
    -0.41
     lusso
    -0.41
    POSITIVE LOGITS
    絶対に
    0.67
    確実に
    0.63
    OGND
    0.61
     Wikimedijinoj
    0.57
     definitely
    0.54
     Definitely
    0.53
     positively
    0.53
    Definitely
    0.50
     unequivocally
    0.50
    PositiveButton
    0.49
    Act Density 0.063%

    No Known Activations