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

    Neuronpedia

    INDEX
    Explanations

    email after comma in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ทรั
    0.97
     NGO
    0.95
     انگ
    0.92
    єд
    0.91
    ឱ
    0.91
    แข
    0.91
    </h2>
    0.89
    NGO
    0.88
     demeure
    0.88
     NGOs
    0.88
    POSITIVE LOGITS
     وكذلك
    1.21
    ₂,
    1.17
     以及
    1.15
    以及
    1.14
    或者是
    1.13
    (),
    1.10
    一个
    1.10
     તેમજ
    1.09
    ,(
    1.08
     that
    1.08
    Act Density 0.355%

    No Known Activations