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

    Neuronpedia

    INDEX
    Explanations

    green light or jetstream going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بیچ
    0.45
     le
    0.42
     Perseverance
    0.41
     pleasing
    0.40
     ele
    0.40
     succ
    0.39
     cháy
    0.38
    ခံ
    0.38
     نعمت
    0.37
    ⏟
    0.37
    POSITIVE LOGITS
     curviliné
    0.66
     carénés
    0.62
     ซ
    0.61
     возле
    0.61
     régler
    0.60
     estudar
    0.59
    gameField
    0.59
    entario
    0.58
    ethyst
    0.57
     basilaires
    0.56
    Act Density 3.166%

    No Known Activations