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
    ات
    1.37
    त
    1.16
    ل
    1.14
    ت
    1.12
    و
    1.08
    る
    1.02
    ко
    1.02
    и
    0.96
     يك
    0.94
     μια
    0.92
    POSITIVE LOGITS
     a
    0.93
    AST
    0.75
    EV
    0.75
    IAN
    0.74
    EST
    0.71
    IOR
    0.69
    ELL
    0.68
    ድግዳ
    0.68
    ain
    0.68
    PLE
    0.67
    Act Density 0.468%

    No Known Activations