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

    Neuronpedia

    INDEX
    Explanations

    g followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     （
    0.88
     (
    0.86
    （
    0.81
     ($\
    0.77
     ($
    0.74
     (_
    0.74
     (**
    0.73
     (*
    0.72
     (\
    0.71
     ({
    0.69
    POSITIVE LOGITS
    .,
    3.28
    .:
    2.69
    .,"
    2.33
    .;
    2.30
    .).
    2.29
    .):
    2.29
    .!
    2.00
    .);
    1.96
    ..,
    1.87
    .?
    1.87
    Act Density 0.300%

    No Known Activations