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

    Neuronpedia

    INDEX
    Explanations

    our little corner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    بت
    0.50
    стема
    0.48
    问题
    0.47
    تع
    0.46
     sepan
    0.46
    iewa
    0.46
    ضع
    0.45
    𝐠
    0.45
    ות
    0.45
    mite
    0.45
    POSITIVE LOGITS
    rip
    0.57
     지정
    0.54
    ㅣ
    0.54
     గా
    0.50
     ধাক
    0.49
     লিখে
    0.48
     пришли
    0.48
     왔
    0.48
     প্ল্যাট
    0.48
     ლი
    0.47
    Act Density 0.000%

    No Known Activations