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

    Neuronpedia

    INDEX
    Explanations

    Deuteronomy and programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.90
    د
    0.75
    ب
    0.75
    de
    0.71
    à
    0.68
    az
    0.68
    д
    0.64
    a
    0.64
    че
    0.63
    지
    0.63
    POSITIVE LOGITS
    </h4>
    0.63
    </b>
    0.63
    )">
    0.58
    $...
    0.57
     randomIndex
    0.56
     YOU
    0.56
    elijke
    0.54
    ्रल
    0.54
    Siehe
    0.54
    )।
    0.53
    Act Density 0.001%

    No Known Activations