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

    Neuronpedia

    INDEX
    Explanations

    winning excellence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    猡
    -2.45
     '
    -2.42
     asesin
    -2.28
     expedited
    -2.17
    "",
    -2.16
    ="")
    -2.11
    ='')
    -2.09
     juzg
    -2.09
    逦
    -2.08
    全力
    -2.06
    POSITIVE LOGITS
    ねぇ
    2.48
    Without
    2.48
    During
    2.45
    Maybe
    2.41
    Usually
    2.38
    All
    2.33
    Though
    2.33
    Many
    2.31
    Before
    2.25
    Although
    2.25
    Act Density 0.013%

    No Known Activations