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

    Neuronpedia

    INDEX
    Explanations

    to be used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gelişmeler
    0.46
     বলিলেন
    0.39
    endif
    0.39
    Sey
    0.38
    ệu
    0.38
     beschik
    0.37
    inations
    0.37
    мець
    0.36
    變得
    0.36
    ई
    0.36
    POSITIVE LOGITS
     used
    1.23
     digunakan
    1.20
     Used
    1.13
     используется
    1.09
     use
    1.08
     gebruikt
    1.07
     utilisée
    1.05
     används
    1.05
     kullanılır
    1.05
     usada
    1.04
    Act Density 0.156%

    No Known Activations