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

    Neuronpedia

    INDEX
    Explanations

    quality and goodness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cameo
    0.73
    Must
    0.70
    Deze
    0.69
    Das
    0.68
    Situation
    0.66
    Row
    0.64
    ний
    0.62
     Deze
    0.62
    companion
    0.62
    Ber
    0.61
    POSITIVE LOGITS
     quality
    1.19
     calidad
    1.09
     berkualitas
    1.07
     गुणवत्ता
    1.06
    质量
    1.05
    quality
    1.03
     qualidade
    1.03
     ಗುಣ
    1.01
     chất
    1.01
    คุณภาพ
    0.99
    Act Density 0.017%

    No Known Activations