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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating uncertainty or possibility

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

    indicating possibility or potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.68
    Personendaten
    -0.68
    Билгалдахарш
    -0.67
     للمعارف
    -0.62
     Савезне
    -0.60
     Houſe
    -0.60
    Hozzáférés
    -0.60
    featureID
    -0.59
    Autoritní
    -0.59
     disambiguazione
    -0.59
    POSITIVE LOGITS
     may
    0.46
     可能
    0.45
     likely
    0.43
     should
    0.41
     plazo
    0.41
     might
    0.40
    可能
    0.40
     Olímpicos
    0.40
     debió
    0.40
    cause
    0.39
    Act Density 0.048%

    No Known Activations