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

    Neuronpedia

    INDEX
    Explanations

    divi, deficit, workforce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    個
    0.51
     पोलिस
    0.48
    啊
    0.47
    ﾇ
    0.46
    وي
    0.46
    ної
    0.46
    接口
    0.46
    多
    0.46
    액
    0.45
    時間
    0.45
    POSITIVE LOGITS
     trustee
    0.51
     anthropologist
    0.47
    an
    0.46
     Mary
    0.46
     directs
    0.46
     draws
    0.45
     Timberlake
    0.45
    oty
    0.44
     Day
    0.44
    ties
    0.44
    Act Density 0.001%

    No Known Activations