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

    Neuronpedia

    INDEX
    Explanations

    quién / quienes (who)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    1.64
    to
    1.39
    </h2>
    1.38
    ک
    1.12
    ।
    1.09
    </h4>
    1.08
    0
    1.08
    </td>
    1.02
     edificio
    1.02
     이
    1.00
    POSITIVE LOGITS
    c
    1.41
    ють
    1.33
    ين
    1.31
    gawa
    1.02
    يده
    0.96
    a
    0.96
    தி
    0.96
    [{}\
    0.96
     won
    0.95
    يب
    0.95
    Act Density 0.001%

    No Known Activations