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

    Neuronpedia

    INDEX
    Explanations

    Around prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (`/
    0.82
    ("_
    0.78
    (`${
    0.77
    (`<
    0.76
    ('_
    0.76
    ("*
    0.74
     („
    0.72
    ('*
    0.71
    ("-
    0.71
    (`
    0.71
    POSITIVE LOGITS
     $
    1.53
    $
    0.89
     अमेरिकी
    0.84
     अमेरिका
    0.83
     лиде
    0.80
     US
    0.78
    ઇ
    0.78
     sorprendente
    0.75
    Trend
    0.75
     américains
    0.75
    Act Density 0.074%

    No Known Activations