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

    Neuronpedia

    INDEX
    Explanations

    try me, bit quantization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    וס
    0.50
    ש
    0.48
    審査
    0.48
    レビュー
    0.46
     diciembre
    0.46
    ີ
    0.45
    ֵ
    0.45
    ופ
    0.43
    朧
    0.43
    И
    0.43
    POSITIVE LOGITS
     Dell
    0.44
     for
    0.43
    Dell
    0.43
    για
    0.43
     برای
    0.42
    Sci
    0.42
     stick
    0.41
     is
    0.38
     eind
    0.38
     त्यासाठी
    0.38
    Act Density 0.009%

    No Known Activations