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

    Neuronpedia

    INDEX
    Explanations

    Chip Readers, steal it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     philanthrop
    0.47
    犯罪
    0.46
    生活的
    0.46
     deputies
    0.45
    icherweise
    0.45
     imitation
    0.45
     partying
    0.44
    俱乐
    0.44
     housewives
    0.44
     disenfranch
    0.43
    POSITIVE LOGITS
     BoxFit
    0.50
    стон
    0.48
     مف
    0.48
     المف
    0.48
     SizedBox
    0.48
     いる
    0.47
     അത്
    0.47
     ވަ
    0.47
     pravi
    0.46
     പതി
    0.46
    Act Density 0.000%

    No Known Activations