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

    Neuronpedia

    INDEX
    Explanations

    considered dominant men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.45
    a
    1.05
    ’”
    0.96
    া
    0.93
    (
    0.86
    tedir
    0.86
    ه
    0.85
    اً
    0.80
    -
    0.75
    岃
    0.75
    POSITIVE LOGITS
    to
    1.15
    و
    1.09
    in
    1.08
    на
    0.99
    다
    0.98
    ள்ளது
    0.96
    ко
    0.96
    י
    0.95
    о
    0.93
    </em>
    0.92
    Act Density 0.680%

    No Known Activations