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

    Neuronpedia

    INDEX
    Explanations

    locations, weather, cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌کند
    0.38
     całej
    0.38
    ของเรา
    0.36
     AdWords
    0.36
     voisines
    0.36
     parois
    0.35
    समा
    0.35
    auz
    0.35
     dioc
    0.35
    DisplayName
    0.35
    POSITIVE LOGITS
    ING
    0.52
    ৫
    0.49
     }^{*
    0.49
    I
    0.49
    4
    0.48
    си
    0.44
    ৪
    0.44
    да
    0.44
    s
    0.44
    3
    0.43
    Act Density 0.055%

    No Known Activations