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

    Neuronpedia

    INDEX
    Explanations

    neural networks and nodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কে
    1.03
    ні
    1.03
    ق
    1.03
    ный
    1.00
    지
    0.99
    ด์
    0.92
    اد
    0.92
    եր
    0.88
    ın
    0.88
    ные
    0.86
    POSITIVE LOGITS
    L
    0.80
     aument
    0.76
    "?
    0.74
    "
    0.74
    J
    0.74
    ↵
    0.72
     for
    0.71
            
    0.70
     declar
    0.70
     agreg
    0.69
    Act Density 0.379%

    No Known Activations