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

    Neuronpedia

    INDEX
    Explanations

    new videos, news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famously
    0.46
    只需
    0.41
    只需要
    0.38
     Everyone
    0.36
     সকলেই
    0.35
    每年
    0.35
     Primarily
    0.35
    یثیت
    0.33
    を指定
    0.33
     solely
    0.32
    POSITIVE LOGITS
     новых
    0.80
     новые
    0.73
     vídeos
    0.73
     새로운
    0.72
     videos
    0.70
     notícias
    0.70
     новый
    0.68
     vídeo
    0.68
     interessante
    0.68
     nuevas
    0.68
    Act Density 0.000%

    No Known Activations