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

    Neuronpedia

    INDEX
    Explanations

    linear algebra operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     상
    0.44
     মাত্র
    0.44
    Constr
    0.44
    彬
    0.44
    $\,.
    0.43
     혼
    0.42
     от
    0.42
    Исход
    0.41
    Н
    0.41
     개발
    0.41
    POSITIVE LOGITS
     vuông
    0.46
     nếu
    0.45
     flowing
    0.43
     angling
    0.43
     organisation
    0.43
     squarely
    0.43
     directement
    0.42
     sorpresa
    0.42
     If
    0.41
    شاء
    0.41
    Act Density 0.001%

    No Known Activations