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

    Neuronpedia

    INDEX
    Explanations

    announcement, announce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.45
    .
    1.37
     -
    1.29
     in
    1.27
     (
    1.16
     =
    1.07
     .
    1.05
      
    1.03
     dụng
    1.03
     который
    1.02
    POSITIVE LOGITS
    is
    1.43
     announcement
    1.16
     Announcement
    1.09
    annonce
    1.08
    ‌ها
    1.07
    ه‌ها
    1.07
    announce
    1.06
    announced
    1.05
    오
    1.03
    リ
    1.02
    Act Density 0.010%

    No Known Activations