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

    Neuronpedia

    INDEX
    Explanations

    hour out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CMOS
    0.52
     hyperparameters
    0.48
     polycarbonate
    0.45
     satin
    0.45
     Biot
    0.44
     corrispond
    0.44
     comunica
    0.44
     reactive
    0.43
     caractères
    0.43
     potrà
    0.42
    POSITIVE LOGITS
    产品
    0.48
    ซื้อ
    0.47
    买
    0.45
    ሪ
    0.43
    어
    0.43
    色々
    0.43
    长
    0.43
    제품
    0.42
     कॅ
    0.42
     खरीदारी
    0.41
    Act Density 0.004%

    No Known Activations