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

    Neuronpedia

    INDEX
    Explanations

    welcome and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    אם
    0.46
    》，
    0.46
    闭
    0.44
    dotnet
    0.43
    故事
    0.42
    o
    0.42
     stepping
    0.42
    寻
    0.42
    বঙ্গের
    0.41
    ại
    0.41
    POSITIVE LOGITS
     خالی
    0.57
     시간을
    0.52
    یہ
    0.50
     빠
    0.50
     useParams
    0.49
     absorbent
    0.48
    ніше
    0.47
     hanno
    0.47
    ાર્થના
    0.47
     personali
    0.46
    Act Density 0.000%

    No Known Activations