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

    Neuronpedia

    INDEX
    Explanations

    nationalities and associated topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िया
    0.70
     शिक्षकों
    0.67
     vô
    0.64
    اد
    0.64
    ين
    0.63
    ুর
    0.62
     każdy
    0.62
    ز
    0.62
    إذا
    0.61
    š
    0.60
    POSITIVE LOGITS
    land
    0.74
     manca
    0.72
    malign
    0.71
    ifting
    0.70
    illiant
    0.69
    cl
    0.69
    men
    0.69
    mag
    0.68
    to
    0.68
    mailed
    0.68
    Act Density 1.116%

    No Known Activations