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

    Neuronpedia

    INDEX
    Explanations

    attention to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كله
    0.50
    isFullscreen
    0.49
     वर्च
    0.49
    SendData
    0.49
     vü
    0.49
     konuş
    0.49
     القدر
    0.48
    鼗
    0.48
    ığım
    0.48
    swarm
    0.48
    POSITIVE LOGITS
    ियो
    0.46
    >$
    0.44
     amenity
    0.43
     requested
    0.42
    ใช้งาน
    0.42
    গত
    0.42
    ля
    0.42
    そこ
    0.40
     arrows
    0.39
    ือ
    0.39
    Act Density 0.001%

    No Known Activations