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

    Neuronpedia

    INDEX
    Explanations

    bullet points and starting points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    министра
    0.65
    banners
    0.65
    सीबी
    0.65
    ürü
    0.62
    াধ
    0.62
    ínu
    0.61
     tartal
    0.61
    രിയ
    0.60
    ேத
    0.59
     ederim
    0.58
    POSITIVE LOGITS
     point
    5.89
     points
    5.81
     Point
    5.33
     Points
    5.28
    Point
    5.20
    point
    5.19
    points
    5.03
    Points
    4.98
    点
    4.72
     puntos
    4.68
    Act Density 0.608%

    No Known Activations