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

    Neuronpedia

    INDEX
    Explanations

    opportunities, benefits, waste, event, conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     percents
    1.02
    拗
    1.00
     items
    0.96
     percentages
    0.92
     percentile
    0.87
     percent
    0.86
    এ
    0.84
     noticeable
    0.84
     austenitic
    0.83
     amps
    0.82
    POSITIVE LOGITS
    ,
    1.44
    ;
    1.21
    .
    1.09
    :
    1.09
     (
    1.04
    UD
    0.97
    (
    0.96
    ؛
    0.95
    it
    0.93
    ،
    0.91
    Act Density 0.014%

    No Known Activations