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

    Neuronpedia

    INDEX
    Explanations

    blouse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    0.89
    لین
    0.80
     rato
    0.72
    लिन
    0.70
     Lakewood
    0.70
     dominions
    0.70
    رین
    0.69
    л
    0.69
     jūs
    0.68
    นั่ง
    0.67
    POSITIVE LOGITS
    O
    1.03
    :
    0.98
    *
    0.93
    ',
    0.92
    +
    0.91
    <
    0.90
    ),
    0.89
    {
    0.86
    );
    0.85
    >
    0.84
    Act Density 0.001%

    No Known Activations