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

    Neuronpedia

    INDEX
    Explanations

    important / what I can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ДК
    0.39
    ugd
    0.39
    ลอง
    0.38
     Idha
    0.37
    ﾚ
    0.37
     Bonne
    0.37
    গার
    0.36
     λοι
    0.36
     मुझ
    0.35
    试试
    0.35
    POSITIVE LOGITS
     important
    0.60
    Instead
    0.60
     महत्वपूर्ण
    0.58
     önemli
    0.58
    Important
    0.56
     важно
    0.55
     crucial
    0.54
    重要な
    0.53
     wichtigen
    0.52
    important
    0.51
    Act Density 0.001%

    No Known Activations