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

    Neuronpedia

    INDEX
    Explanations

    time taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    질
    0.43
    และการ
    0.42
    optimization
    0.41
     सित
    0.41
    owment
    0.41
    的使用
    0.40
     какую
    0.40
     работу
    0.40
    wertung
    0.40
    ൨
    0.40
    POSITIVE LOGITS
     them
    0.51
     देम
    0.41
    GameObject
    0.40
     chosen
    0.38
     CNN
    0.38
     THEM
    0.37
     privat
    0.36
    níků
    0.36
    某个
    0.36
     coals
    0.36
    Act Density 0.004%

    No Known Activations