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

    Neuronpedia

    INDEX
    Explanations

    delivering quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assez
    0.51
     αρκε
    0.51
     khá
    0.50
    較
    0.48
     dość
    0.46
     bastante
    0.46
     довольно
    0.45
     cukup
    0.45
     досить
    0.45
     Relatively
    0.42
    POSITIVE LOGITS
     quality
    1.42
     каче
    1.41
    高品質
    1.38
     exceptional
    1.38
    高质量
    1.35
    优质
    1.28
     hochwert
    1.27
    quality
    1.26
     hochwertige
    1.26
     berkualitas
    1.23
    Act Density 0.054%

    No Known Activations