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

    Neuronpedia

    INDEX
    Explanations

    India, fonts, food, game_over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ترض
    0.61
    テム
    0.59
     Guille
    0.59
    푐
    0.58
    ويل
    0.58
    ⵄ
    0.56
    讠
    0.54
     وه
    0.54
    Pont
    0.54
     பாபிலோ
    0.54
    POSITIVE LOGITS
     India
    1.98
     Indian
    1.76
     Delhi
    1.73
    India
    1.73
    印度
    1.69
     Mumbai
    1.68
     india
    1.63
     INDIA
    1.63
     Chennai
    1.62
     Maharashtra
    1.59
    Act Density 0.026%

    No Known Activations