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

    Neuronpedia

    INDEX
    Explanations

    years and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ribs
    0.40
     zona
    0.37
    あまり
    0.37
     spline
    0.37
     globules
    0.36
    デス
    0.35
     larynx
    0.35
     Smiling
    0.35
    紋
    0.34
     ਇੱਕ
    0.34
    POSITIVE LOGITS
     წლის
    0.54
     vuoden
    0.52
     edition
    0.51
    年的
    0.50
     aasta
    0.48
     election
    0.48
    क्षणिक
    0.46
    春夏
    0.46
    秋冬
    0.46
     Almanac
    0.46
    Act Density 0.040%

    No Known Activations