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

    Neuronpedia

    INDEX
    Explanations

    shaped area, wider than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     only
    0.54
    5
    0.54
    1
    0.50
    не
    0.49
    ні
    0.47
     নিতান্ত
    0.47
    ನ್
    0.47
    ５
    0.46
     to
    0.46
    １
    0.45
    POSITIVE LOGITS
     கீழ
    0.48
    ⚒
    0.43
    ↞
    0.42
    lukan
    0.42
     जागरूकता
    0.41
     Burke
    0.41
     книга
    0.41
    باً
    0.40
     কণ
    0.40
    หมือน
    0.40
    Act Density 0.004%

    No Known Activations