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

    Neuronpedia

    INDEX
    Explanations

    special characters and diacritical marks in various languages

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

    with diacritics

    np_acts-logits-general · gemini-2.0-flash

    accented vowels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.81
    Slf
    -0.67
    linawan
    -0.66
     المعيارى
    -0.66
     nahilalakip
    -0.65
    !*\
    -0.64
    󠁣
    -0.62
     informée
    -0.61
    󠁮
    -0.61
    FormTagHelper
    -0.60
    POSITIVE LOGITS
    <?
    0.47
     MÉXICO
    0.45
     láser
    0.43
     Bengaluru
    0.43
     vPvB
    0.42
    œil
    0.41
     Kanada
    0.41
    臺
    0.41
    technologies
    0.40
    ++];
    0.40
    Act Density 0.448%

    No Known Activations