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

    Neuronpedia

    INDEX
    Explanations

    plot or character ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ס
    1.16
    m
    1.13
    ו
    1.12
    σ
    1.11
    و
    1.08
    ר
    1.08
    டன்
    1.04
    тных
    1.00
    taking
    1.00
    zal
    0.99
    POSITIVE LOGITS
     personnage
    1.15
    аны
    1.08
    ıml
    1.06
     suspense
    1.05
    वस्तु
    1.03
    ҙ
    1.02
    人物
    0.98
     طریقے
    0.98
    ıları
    0.98
    ные
    0.98
    Act Density 0.549%

    No Known Activations