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

    Neuronpedia

    INDEX
    Explanations

    choose the most proper one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дзяржа
    0.55
     infrastrukt
    0.55
    湎
    0.53
    舢
    0.51
     praticamente
    0.50
     antennis
    0.50
     சுண்ணாம்பு
    0.49
    髖
    0.49
     anses
    0.49
     slecht
    0.48
    POSITIVE LOGITS
     Xia
    0.56
     Xiao
    0.55
    ！
    0.55
     according
    0.54
     WeChat
    0.54
    根据
    0.54
    丨
    0.51
     exquisite
    0.51
    xiang
    0.50
    ：
    0.50
    Act Density 0.029%

    No Known Activations