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

    Neuronpedia

    INDEX
    Explanations

    Google company information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngày
    0.56
    de
    0.55
     необходимо
    0.54
    CT
    0.52
     актив
    0.51
    gou
    0.51
    <unused37>
    0.51
    arat
    0.51
    arial
    0.51
     dotycz
    0.50
    POSITIVE LOGITS
    の
    0.58
    的区别
    0.57
    風味
    0.56
    语
    0.53
     breath
    0.52
    物
    0.51
    相
    0.50
    ངས་
    0.50
    ਮ
    0.49
    の違い
    0.49
    Act Density 0.002%

    No Known Activations