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

    Neuronpedia

    INDEX
    Explanations

    trying to, hoping to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    点的
    0.95
     points
    0.88
     نقاط
    0.81
     point
    0.80
    points
    0.80
    点の
    0.80
    点
    0.79
    點
    0.78
    Point
    0.76
    点了
    0.76
    POSITIVE LOGITS
     Pron
    0.46
     Gat
    0.43
     Hone
    0.42
     pron
    0.41
    䏌
    0.41
     gat
    0.40
     Valle
    0.38
     dash
    0.38
    ToBe
    0.38
     valle
    0.38
    Act Density 0.113%

    No Known Activations