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

    Neuronpedia

    INDEX
    Explanations

    countries and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agré
    0.52
     qué
    0.51
     çalışma
    0.50
     प्रमाण
    0.49
     महाराष्ट्रा
    0.49
     kült
    0.49
    ަލ
    0.49
     mene
    0.48
     காங்க
    0.48
    crisis
    0.48
    POSITIVE LOGITS
     ইলেক্ট্রোলাই
    0.57
    चीत
    0.56
    торы
    0.54
    是非常
    0.54
     atrial
    0.54
    更为
    0.53
    딛
    0.52
    .,
    0.52
    रावर
    0.52
    ೋಜನ
    0.52
    Act Density 0.020%

    No Known Activations