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

    Neuronpedia

    INDEX
    Explanations

    Data structures and functional types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stats
    0.42
    **(
    0.41
     (**
    0.40
    (**
    0.39
    **
    0.39
     **
    0.38
    zb
    0.38
    itmen
    0.38
     oriente
    0.38
    mesi
    0.38
    POSITIVE LOGITS
    ലും
    0.43
    [{{
    0.43
    Later
    0.40
    会的
    0.40
    屆
    0.39
    [
    0.39
    也会
    0.38
    шь
    0.38
    льний
    0.38
    中的
    0.38
    Act Density 0.009%

    No Known Activations