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

    Neuronpedia

    INDEX
    Explanations

    luxury accommodations and amenities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    劑
    0.37
    啮
    0.31
     Giveen
    0.31
    erol
    0.31
    第一百
    0.30
    umbered
    0.30
     popOperand
    0.30
    味料
    0.29
    恤
    0.29
    ણી
    0.29
    POSITIVE LOGITS
     luxury
    0.68
     luxurious
    0.64
     luxe
    0.61
     gourmet
    0.61
     modern
    0.60
    luxury
    0.55
     designer
    0.55
     jacuzzi
    0.54
     lux
    0.53
     Luxury
    0.53
    Act Density 0.003%

    No Known Activations