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

    Neuronpedia

    INDEX
    Explanations

    numbers following symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sixty
    0.73
     Integer
    0.70
     Fifty
    0.69
     '*'
    0.68
    जग
    0.67
     Seventy
    0.66
    ូង
    0.65
     смысла
    0.64
     Thirty
    0.63
     Eighty
    0.63
    POSITIVE LOGITS
    (.
    1.53
    =.
    1.44
     (.
    1.35
    -.
    1.02
    <.
    0.92
     tenths
    0.92
    [.
    0.91
    /.
    0.90
     -.
    0.89
     +.
    0.88
    Act Density 0.329%

    No Known Activations