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

    Neuronpedia

    INDEX
    Explanations

    roads and infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كل
    0.64
    ку
    0.61
     تي
    0.61
    vý
    0.59
     método
    0.58
     моделей
    0.56
     жизнью
    0.56
     conjunto
    0.55
     různých
    0.55
    ين
    0.54
    POSITIVE LOGITS
     roads
    0.89
    n
    0.82
     you
    0.75
    roads
    0.74
     that
    0.71
     highways
    0.69
     I
    0.68
    س
    0.68
    <0x98>
    0.65
     Roads
    0.65
    Act Density 0.003%

    No Known Activations