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

    Neuronpedia

    INDEX
    Explanations

    decorating objects and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    1.23
    1
    1.20
    OM
    1.12
     i
    1.04
     repas
    1.03
    ¹.
    0.97
    OS
    0.96
     at
    0.95
    CT
    0.93
     protégé
    0.93
    POSITIVE LOGITS
     decorations
    1.12
    decorated
    1.09
     Decorations
    1.08
    ному
    1.05
    ни
    1.01
    ivatives
    0.95
    飾り
    0.95
    т
    0.94
    нок
    0.91
     decorating
    0.91
    Act Density 0.015%

    No Known Activations