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

    Neuronpedia

    INDEX
    Explanations

    introducing comparisons or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ad
    1.23
    uk
    1.21
    il
    1.19
     powied
    1.09
    <0x80>
    1.04
    EST
    1.04
     are
    1.00
     minat
    0.98
    ۰
    0.98
     zacz
    0.95
    POSITIVE LOGITS
    '
    1.65
    .
    1.11
    در
    1.09
    은
    1.09
    iers
    1.05
    ज
    1.02
    in
    1.00
    มัน
    1.00
    هم
    0.99
    는
    0.98
    Act Density 0.235%

    No Known Activations