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

    Neuronpedia

    INDEX
    Explanations

    lists with asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     സൃഷ്ട
    0.46
     httpServer
    0.46
     dụng
    0.45
     bởi
    0.45
    为
    0.44
    贫
    0.44
    员工
    0.44
     étudi
    0.43
    设备的
    0.43
    饮食
    0.43
    POSITIVE LOGITS
    かもしれない
    0.53
     خواهد
    0.52
    可能會
    0.51
     خواهند
    0.50
    也會
    0.50
    かもしれません
    0.47
    隴
    0.47
    angani
    0.45
     ಮತ್ತೆ
    0.43
     eventually
    0.43
    Act Density 0.007%

    No Known Activations