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

    Neuronpedia

    INDEX
    Explanations

    card names and ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лды
    1.08
     lessening
    1.06
    ды
    0.91
     plunging
    0.88
    Databaze
    0.87
     повышен
    0.84
    ց
    0.83
     upbringing
    0.83
    瘠
    0.83
    чает
    0.82
    POSITIVE LOGITS
    ，
    0.94
    。
    0.91
    я
    0.88
    ،
    0.87
    THREE
    0.83
    राना
    0.82
    因而
    0.82
    、
    0.82
    ف
    0.81
     égaux
    0.80
    Act Density 0.002%

    No Known Activations