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

    Neuronpedia

    INDEX
    Explanations

    news urls and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Lateral
    0.44
    麃
    0.43
    Intermediate
    0.42
    หลัก
    0.40
    烔
    0.40
     تھی۔
    0.40
    厡
    0.40
     Lateral
    0.39
    醀
    0.39
    堭
    0.39
    POSITIVE LOGITS
     noticias
    0.51
    news
    0.50
     news
    0.47
     noticia
    0.47
     notícia
    0.45
    ji
    0.44
     voli
    0.44
    weixin
    0.44
    Ⅴ
    0.44
     notícias
    0.43
    Act Density 0.001%

    No Known Activations