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

    Neuronpedia

    INDEX
    Explanations

    JSON structure punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :)
    0.87
    (:
    0.80
    )((
    0.80
    )^(
    0.77
    })();
    0.76
    :-)
    0.75
    )(-
    0.71
    (=
    0.69
    ((
    0.69
    (-)
    0.67
    POSITIVE LOGITS
     [],
    1.38
     [
    1.28
     ["
    1.26
     []
    1.06
     ['
    0.96
     []),
    0.95
     [])
    0.94
     ['.
    0.90
     [{"
    0.89
     ['(?
    0.86
    Act Density 0.052%

    No Known Activations