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

    Neuronpedia

    INDEX
    Explanations

    universal characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zheng
    0.59
     chois
    0.59
    ড়াল
    0.57
    ⃘
    0.57
    쟁
    0.56
    iz
    0.55
    ोसिएशन
    0.55
     Dieu
    0.54
     informée
    0.54
     Racing
    0.54
    POSITIVE LOGITS
    ک
    0.80
    æ
    0.79
    ة
    0.76
    ل
    0.71
    ী
    0.66
    z
    0.66
    ק
    0.66
    ر
    0.63
     do
    0.63
    лете
    0.63
    Act Density 0.000%

    No Known Activations