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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ぇ
    2.29
    În
    2.18
     În
    2.15
    РА
    2.14
    Не
    2.11
    ろん
    2.09
    ตรี
    2.05
    лі
    2.03
     মানবতার
    2.01
    錢
    1.96
    POSITIVE LOGITS
    ITY
    2.67
    ity
    2.63
    ities
    2.57
    ized
    2.31
    ität
    2.26
    ization
    2.22
    itet
    2.21
    izacja
    2.11
    IZATION
    2.03
    তাবাদ
    2.02
    Act Density 1.780%

    No Known Activations