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

    Neuronpedia

    INDEX
    Explanations

    **/**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     remarkably
    1.03
    janja
    0.92
     forhold
    0.92
    nega
    0.90
     widely
    0.88
    quam
    0.87
    loft
    0.87
     Cowboy
    0.86
     einmal
    0.86
     strikingly
    0.86
    POSITIVE LOGITS
     업체
    1.22
     제작
    1.18
     xây
    1.08
    手工
    1.06
     디지털
    1.04
    專業
    1.03
    Printed
    1.01
     출력
    1.01
     전문가
    0.99
    темати
    0.99
    Act Density 24.431%

    No Known Activations