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

    Neuronpedia

    INDEX
    Explanations

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aży
    0.46
     стандарт
    0.45
     Manajemen
    0.45
     нового
    0.44
     финансовых
    0.43
     Народ
    0.43
     ट्रायल
    0.42
     sayılı
    0.42
     стоимости
    0.42
     лучшие
    0.42
    POSITIVE LOGITS
    可以是
    0.48
    string
    0.46
    also
    0.46
    the
    0.45
    str
    0.45
    down
    0.44
    也可以
    0.43
    空间
    0.43
    th
    0.42
    tong
    0.42
    Act Density 0.011%

    No Known Activations