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

    Neuronpedia

    INDEX
    Explanations

    non-English characters and symbols, reflecting an interest in diverse languages or writing systems

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

    Non-English text/characters

    np_acts-logits-general · gemini-2.0-flash

    plural forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.77
     disambiguazione
    -0.65
    alyptus
    -0.64
    esgue
    -0.58
    ineno
    -0.57
    ANSAS
    -0.52
    出版年
    -0.51
     Wikispecies
    -0.51
    ArgsConstructor
    -0.51
    ValueStyle
    -0.50
    POSITIVE LOGITS
    들
    0.80
    们
    0.76
    們
    0.75
    들은
    0.73
    ów
    0.72
    들을
    0.71
    達
    0.70
    들이
    0.69
    lar
    0.64
    们的
    0.64
    Act Density 0.049%

    No Known Activations