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

    Neuronpedia

    INDEX
    Explanations

    russian language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    および
    0.89
     పేర్కొ
    0.87
    具有
    0.78
    旨在
    0.77
     प्रदान
    0.73
     menggunakan
    0.72
     utilizing
    0.71
     oluştur
    0.71
    ிலான
    0.69
     ensuring
    0.69
    POSITIVE LOGITS
     poquito
    1.20
     bisschen
    1.13
     бывает
    1.10
     Сейчас
    1.07
     деньги
    1.06
     dinheiro
    1.06
    ))
    1.03
     trochę
    1.02
     helemaal
    1.01
     terribly
    1.01
    Act Density 0.073%

    No Known Activations