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

    Neuronpedia

    INDEX
    Explanations

    Northern Hemisphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    2.72
    lös
    2.17
    기
    2.06
    ー
    2.03
    িক
    1.86
    льним
    1.82
    اً
    1.81
    er
    1.77
    är
    1.70
    ాయ
    1.70
    POSITIVE LOGITS
    い
    2.98
    י
    2.28
    いだ
    2.20
     uglify
    1.95
     Shroff
    1.91
    ころ
    1.91
     Regards
    1.86
    اریخ
    1.85
    ことを
    1.82
    ی
    1.82
    Act Density 0.001%

    No Known Activations