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

    Neuronpedia

    INDEX
    Explanations

    nationalities and cultural associations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मा
    0.58
     मौजूद
    0.57
     isang
    0.57
     Grassmann
    0.57
     inglês
    0.55
    지
    0.55
    做
    0.55
     των
    0.54
     áreas
    0.54
     spécifiques
    0.54
    POSITIVE LOGITS
     cuisine
    0.67
     proverb
    0.56
     Cuisine
    0.54
     nationality
    0.54
    istani
    0.49
     consulate
    0.48
    ys
    0.47
    ország
    0.47
    ess
    0.46
     nationalism
    0.46
    Act Density 0.071%

    No Known Activations