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

    Neuronpedia

    INDEX
    Explanations

    the table

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     woning
    0.88
     घरा
    0.87
    住在
    0.82
     घरी
    0.82
     casa
    0.80
     ಮನೆಯ
    0.79
     új
    0.79
     rumah
    0.78
     cidade
    0.77
     parques
    0.77
    POSITIVE LOGITS
     tables
    2.20
     table
    1.95
     Tables
    1.80
    tables
    1.79
     테이블
    1.73
    Tables
    1.69
     desks
    1.66
     Table
    1.60
    table
    1.59
    テーブル
    1.59
    Act Density 0.161%

    No Known Activations