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

    Neuronpedia

    INDEX
    Explanations

    dense layers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िक
    1.03
    ส์
    1.03
    ان
    1.02
    न
    0.97
    ıları
    0.88
    ěli
    0.86
    0.85
    िकता
    0.84
    ع
    0.84
    िया
    0.82
    POSITIVE LOGITS
     башка
    0.93
    լ
    0.88
     tonic
    0.87
     nghiệm
    0.87
     pok
    0.86
     protease
    0.86
     adjunct
    0.86
     anten
    0.84
    これにより
    0.83
     teles
    0.82
    Act Density 0.002%

    No Known Activations