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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     നേത
    -0.10
     नेताओं
    -0.09
     വിതരണം
    -0.08
     leaders
    -0.08
     কর্মকর্ত
    -0.08
    .mapreduce
    -0.08
     নেতা
    -0.08
     выплат
    -0.08
     모집
    -0.08
    );
↵
↵
    -0.08
    POSITIVE LOGITS
     household
    0.17
     घर
    0.15
     المنزل
    0.14
     kitchen
    0.13
     ಮನೆಯ
    0.13
    家庭
    0.13
     home's
    0.13
     wife
    0.13
     ઘર
    0.13
    Kitchen
    0.12
    Act Density 0.303%

    No Known Activations