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

    Neuronpedia

    INDEX
    Explanations

    delegates authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тус
    0.43
     معاش
    0.38
    ру
    0.37
     Constant
    0.36
    uniary
    0.36
     Until
    0.36
    ரன்
    0.36
    实践
    0.36
    ради
    0.35
    нуу
    0.35
    POSITIVE LOGITS
     ಮಾಡಿದ್ದಾರೆ
    0.40
    ğmen
    0.39
    ዦ
    0.39
    質量
    0.37
     {:?}",
    0.37
     منتشر
    0.37
     Vorteile
    0.37
    রাট
    0.37
     beste
    0.37
     دارد
    0.36
    Act Density 0.001%

    No Known Activations