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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and associated items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dàng
    1.32
    ด
    1.31
    ﻠ
    1.27
    ০০
    1.26
     Lordships
    1.26
    TERS
    1.25
    もちろん
    1.25
    ە
    1.22
    ۥ
    1.22
    ดัน
    1.21
    POSITIVE LOGITS
    ни
    1.95
    𝘵
    1.44
    ή
    1.34
    ้
    1.32
    Doesn
    1.31
    та
    1.30
    ೇತ್ರ
    1.23
    м
    1.23
    ం
    1.21
    ف
    1.20
    Act Density 0.090%

    No Known Activations