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

    Neuronpedia

    INDEX
    Explanations

    Buildings, castles, landscapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    身体
    0.50
    舞蹈
    0.49
     शारीरिक
    0.47
     hijab
    0.47
     dance
    0.46
     sweaty
    0.46
     चेहरे
    0.46
     spandex
    0.46
     Canvas
    0.45
     Blush
    0.44
    POSITIVE LOGITS
    Buildings
    0.75
     buildings
    0.71
     landscapes
    0.70
     Buildings
    0.65
     castles
    0.65
    buildings
    0.65
     cityscape
    0.64
     edificios
    0.63
    建筑物
    0.63
     edifici
    0.63
    Act Density 0.084%

    No Known Activations