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

    Neuronpedia

    INDEX
    Explanations

    phrases related to familial relationships and identities

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

    Preceding a lowercase "l" or "i"

    np_acts-logits-general · gemini-2.0-flash

    Italian articles and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.78
     تضيفلها
    -0.71
     '\\;'
    -0.71
    出版年
    -0.69
     AssemblyCompany
    -0.67
    PreferredItem
    -0.66
     nakalista
    -0.66
     tabPage
    -0.64
    ]--;
    -0.64
     auroit
    -0.64
    POSITIVE LOGITS
     l
    0.69
     il
    0.64
     i
    0.58
     non
    0.56
     c
    0.53
    il
    0.50
     Non
    0.48
     Il
    0.46
     chi
    0.46
    ButterKnife
    0.45
    Act Density 0.037%

    No Known Activations