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

    Neuronpedia

    INDEX
    Explanations

    royalty and kings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.98
    Przeczytaj
    0.98
    ุ
    0.95
    ם
    0.94
    ја
    0.94
    pere
    0.92
     Burd
    0.92
     डालें
    0.91
     vải
    0.91
    его
    0.91
    POSITIVE LOGITS
     thrones
    1.32
     नरेश
    1.27
    色列
    1.22
     kings
    1.19
     royals
    1.14
     queens
    1.13
    妃
    1.13
     castles
    1.12
    百姓
    1.12
    RO
    1.11
    Act Density 0.101%

    No Known Activations