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

    Neuronpedia

    INDEX
    Explanations

    prices and costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体积
    0.31
    یه
    0.28
    鸴
    0.28
    draggable
    0.28
    sweater
    0.27
    境界層
    0.27
     పదార్థ
    0.27
    紊
    0.26
    泬
    0.26
    วัสดี
    0.26
    POSITIVE LOGITS
     $
    0.41
    1
    0.37
    ти
    0.36
    ла
    0.34
    5
    0.30
    １
    0.29
     ۵
    0.28
    .
    0.28
    ‌
    0.28
     hundreds
    0.28
    Act Density 0.069%

    No Known Activations