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

    Neuronpedia

    INDEX
    Explanations

    kotlin code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्परिक
    0.51
    睒
    0.47
    ጲ
    0.46
    铢
    0.46
     MDET
    0.46
    朳
    0.46
    माष्टमी
    0.46
    ሢ
    0.45
    िडेट
    0.45
     Chirurgien
    0.45
    POSITIVE LOGITS
    3
    0.52
    -
    0.50
    '
    0.49
     and
    0.47
    2
    0.46
    4
    0.46
    N
    0.45
     -
    0.43
     is
    0.42
    s
    0.42
    Act Density 0.002%

    No Known Activations