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

    Neuronpedia

    INDEX
    Explanations

    following female pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ktorý
    1.16
     yourselves
    1.11
     вашей
    1.09
     உங்கள்
    1.08
    娶
    1.07
     तुमच्या
    1.02
     yourself
    1.02
    老婆
    1.01
     kojim
    1.00
    your
    0.99
    POSITIVE LOGITS
     herself
    2.88
    她的
    1.94
    她
    1.90
     نفسها
    1.81
     she
    1.79
     她
    1.75
     miała
    1.73
     เธอ
    1.68
     готова
    1.66
     која
    1.65
    Act Density 0.047%

    No Known Activations