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

    Neuronpedia

    INDEX
    Explanations

    multilingual list item descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     values
    0.48
     parameters
    0.48
    тный
    0.47
     compatible
    0.47
     modals
    0.47
    рио
    0.46
     justified
    0.46
     favoured
    0.46
    _
    0.45
     folos
    0.45
    POSITIVE LOGITS
     അദ്ദേഹ
    0.50
    CLOSED
    0.49
    CLOS
    0.49
    ㄈ
    0.49
    therefore
    0.47
     lbs
    0.46
     Nghi
    0.46
     வளர்ச்ச
    0.46
     گزر
    0.46
     ඉද
    0.45
    Act Density 0.001%

    No Known Activations