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

    Neuronpedia

    INDEX
    Explanations

    mail nickname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kob
    0.49
     nomenclatura
    0.47
    anez
    0.46
    kurs
    0.46
     Ombudsman
    0.46
    ꯣ
    0.45
    kamp
    0.45
    kli
    0.45
    BeforeText
    0.45
    icleta
    0.44
    POSITIVE LOGITS
    陨
    0.48
    グルメ
    0.46
    矵
    0.44
    لا
    0.43
    რობ
    0.43
    し
    0.43
     πο
    0.43
    歌曲
    0.43
    。
    0.43
    ο
    0.42
    Act Density 0.003%

    No Known Activations