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

    Neuronpedia

    INDEX
    Explanations

    full capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Others
    0.41
     recue
    0.41
    اش
    0.41
     deportivas
    0.41
    Цена
    0.40
     بھائی
    0.40
    บ้าง
    0.40
     quir
    0.39
    ಾಮ
    0.39
     amenity
    0.39
    POSITIVE LOGITS
    完成
    0.48
     完成
    0.45
    甪
    0.44
     wundersch
    0.43
    实验室
    0.43
    非常
    0.43
     అత్య
    0.43
    璀
    0.42
    enza
    0.41
    如此
    0.41
    Act Density 0.001%

    No Known Activations