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

    Neuronpedia

    INDEX
    Explanations

    address, Person, movie, Player, items, information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ze
    0.27
    se
    0.24
    𝙧
    0.24
    uak
    0.22
    uwa
    0.22
    瘾
    0.22
    ぁ
    0.22
    ání
    0.21
    vä
    0.21
    sschutz
    0.21
    POSITIVE LOGITS
     координаты
    0.20
     согласо
    0.18
    ዎችን
    0.18
     الاسم
    0.18
     supposing
    0.18
     وتق
    0.18
     lucrat
    0.18
    بانی
    0.18
    Morse
    0.18
     motivi
    0.18
    Act Density 0.783%

    No Known Activations