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

    Neuronpedia

    INDEX
    Explanations

    point or points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ූ
    0.35
    撂
    0.34
    ລັບ
    0.33
    কলে
    0.33
    ەکە
    0.33
    ષ્ય
    0.33
    箩
    0.32
    ⇵
    0.32
    രിക
    0.32
     അറിയി
    0.32
    POSITIVE LOGITS
     point
    4.50
     points
    4.25
    point
    3.98
    points
    3.86
     Point
    3.84
    Point
    3.83
     Points
    3.80
    Points
    3.72
    点
    3.67
     punto
    3.66
    Act Density 0.273%

    No Known Activations