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

    Neuronpedia

    INDEX
    Explanations

    nationalities and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Europe
    0.61
    Europe
    0.53
     Asia
    0.48
     Hawaii
    0.46
     Crimea
    0.46
     沖縄
    0.46
     Yosemite
    0.45
     اروپا
    0.45
     Tibet
    0.45
     Appalach
    0.45
    POSITIVE LOGITS
     nitrification
    0.42
     Polish
    0.39
     slov
    0.37
     Induction
    0.36
     Slovak
    0.36
     Estonian
    0.35
     اسرائیلی
    0.35
     PLN
    0.35
     Hungarian
    0.34
     Improving
    0.34
    Act Density 0.013%

    No Known Activations