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

    Neuronpedia

    INDEX
    Explanations

    burada olmak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅಂಶ
    1.01
     Они
    0.97
    Но
    0.87
     방식
    0.86
    になる
    0.85
     Это
    0.84
    とし
    0.84
     정도로
    0.84
     Tuttavia
    0.83
     Пло
    0.82
    POSITIVE LOGITS
     daha
    1.00
     sadece
    0.96
     çok
    0.95
     kendi
    0.93
     nasıl
    0.86
     zaman
    0.83
     farklı
    0.83
     aynı
    0.83
     belirli
    0.81
     herhangi
    0.80
    Act Density 0.001%

    No Known Activations