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

    Neuronpedia

    INDEX
    Explanations

    qualities and nuances across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     When
    1.17
    people
    1.02
     เมื่อ
    1.02
     عندما
    1.01
    making
    1.00
    when
    0.99
     when
    0.97
    suits
    0.95
     If
    0.94
     Whenever
    0.94
    POSITIVE LOGITS
    心态
    0.97
     වශ
    0.84
     nuances
    0.83
    א
    0.83
    ف
    0.81
    メリット
    0.80
     හොඳ
    0.79
     знако
    0.79
     нюан
    0.79
     caveats
    0.78
    Act Density 0.386%

    No Known Activations