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

    Neuronpedia

    INDEX
    Explanations

    BCE or centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    라이언트
    0.89
    芏
    0.88
     vacancies
    0.86
    გი
    0.85
     শতাংশ
    0.83
    ্ডিং
    0.82
     chhoti
    0.82
     Kareena
    0.79
    뗑
    0.76
    ನ್ನೂ
    0.75
    POSITIVE LOGITS
    ع
    1.02
    ال
    0.92
     ange
    0.86
     آرام
    0.83
    ो
    0.83
    0
    0.79
    ن
    0.79
    レ
    0.79
     ابن
    0.78
    antera
    0.76
    Act Density 0.001%

    No Known Activations