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

    Neuronpedia

    INDEX
    Explanations

    titles and names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ָ
    0.81
    nhold
    0.79
    ссмо
    0.79
    ัตว์
    0.77
    那我
    0.77
     MAKEINTRESOURCE
    0.76
     टीमें
    0.76
    طيني
    0.75
    爱你
    0.74
    oida
    0.73
    POSITIVE LOGITS
     Mr
    1.81
     Kevin
    1.43
    Mr
    1.41
     Mrs
    1.38
     Michael
    1.38
    这位
    1.35
     Derek
    1.34
     Andrew
    1.33
    這位
    1.32
     آقای
    1.32
    Act Density 1.300%

    No Known Activations