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

    Neuronpedia

    INDEX
    Explanations

    geographical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     courtesy
    0.44
    اؤن
    0.43
    Vậy
    0.42
    avec
    0.42
    Courtesy
    0.41
    Спасибо
    0.40
     Bugünkü
    0.40
    Whatever
    0.40
    Couldn
    0.39
    Escol
    0.39
    POSITIVE LOGITS
     например
    0.50
    某些
    0.50
    บาง
    0.49
     있지만
    0.48
     ឬ
    0.47
     иногда
    0.46
     शहरों
    0.44
     cities
    0.43
     लेकिन
    0.42
    特定的
    0.42
    Act Density 0.003%

    No Known Activations