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

    Neuronpedia

    INDEX
    Explanations

    the following word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Тому
    1.13
     harboring
    1.03
     Jeżeli
    1.00
     tirelessly
    0.98
     Чтобы
    0.96
     Бүген
    0.96
     Поэтому
    0.93
     Бүгенге
    0.93
    ll
    0.93
     Undoubtedly
    0.91
    POSITIVE LOGITS
    ла
    0.96
    什么
    0.89
    ம
    0.89
     asli
    0.88
     మహి
    0.86
    )),
    0.83
    🌔
    0.83
    最
    0.83
    颯
    0.82
    तेश
    0.82
    Act Density 0.143%

    No Known Activations