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

    Neuronpedia

    INDEX
    Explanations

    conjunctions from multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    -2.33
     â
    -2.14
    an
    -2.14
    ,”
    -2.09
    櫺
    -2.05
    푣
    -2.03
    ’,
    -2.02
    鋮
    -1.95
    你
    -1.87
    !”
    -1.86
    POSITIVE LOGITS
    力
    2.16
    茑
    2.08
    ꦠ
    2.03
    茀
    1.98
     lenguas
    1.98
     weichen
    1.94
     фильтр
    1.94
    ада
    1.92
    厖
    1.92
    ↵↵
    1.91
    Act Density 0.001%

    No Known Activations