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

    Neuronpedia

    INDEX
    Explanations

    positive service recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seductive
    0.41
    鯨
    0.39
     multiplicity
    0.39
     উত্তেজ
    0.39
     assumes
    0.38
    偶尔
    0.37
     multiplicities
    0.37
     racc
    0.37
    駆動
    0.37
    щаем
    0.37
    POSITIVE LOGITS
     professionalism
    0.79
     excellent
    0.72
     excelente
    0.72
     Excellent
    0.71
     Helped
    0.70
     staff
    0.68
     excelentes
    0.68
     services
    0.67
     fantastic
    0.67
     خدمات
    0.66
    Act Density 0.008%

    No Known Activations