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

    Neuronpedia

    INDEX
    Explanations

    regardless of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    କ
    0.95
    いた
    0.87
     invertebrates
    0.86
    𝙜
    0.81
    КУ
    0.75
    。\
    0.75
     sureties
    0.74
     mismas
    0.73
    ড
    0.73
    ପ
    0.73
    POSITIVE LOGITS
    is
    1.38
    el
    1.25
    s
    1.14
    of
    1.13
    en
    1.09
    as
    1.02
    ון
    1.02
    ิ
    1.02
    س
    0.99
    ס
    0.97
    Act Density 0.012%

    No Known Activations