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

    Neuronpedia

    INDEX
    Explanations

    descriptive architectural materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     space
    1.09
    space
    1.04
    Space
    1.03
     공간
    1.01
     Space
    0.99
     spaces
    0.99
     Spaces
    0.91
    spaces
    0.88
    Spaces
    0.84
    SPACE
    0.78
    POSITIVE LOGITS
    釭
    1.10
     parquet
    1.07
     carpeting
    1.06
     fixtures
    1.02
     wallpapers
    0.99
     granit
    0.96
     windows
    0.95
     Windows
    0.93
     carpets
    0.92
    xtures
    0.92
    Act Density 0.064%

    No Known Activations