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

    Neuronpedia

    INDEX
    Explanations

    stewing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    1.38
     rejuven
    1.15
     unscrupulous
    1.05
     reorgan
    1.02
     jeopard
    0.97
     añad
    0.95
     prudent
    0.93
     hepat
    0.91
     observant
    0.91
    。
    0.91
    POSITIVE LOGITS
    ul
    1.94
    n
    1.58
    ar
    1.55
    is
    1.51
    w
    1.41
    as
    1.39
    id
    1.33
    i
    1.32
    x
    1.29
    y
    1.28
    Act Density 0.000%

    No Known Activations