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

    Neuronpedia

    INDEX
    Explanations

    she, her, herself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کرتی
    1.14
     dets
    1.13
     رکھتی
    1.12
     बनाती
    1.09
    ின்றான்
    1.08
     boyhood
    1.08
     دیتی
    1.05
     ہوج
    0.97
     करती
    0.94
     ہوتی
    0.93
    POSITIVE LOGITS
     she
    5.23
    她
    5.13
     her
    4.82
    她的
    4.66
     그녀
    4.65
     她
    4.50
    彼女
    4.35
    她在
    4.33
     ఆమె
    4.28
     herself
    4.23
    Act Density 0.636%

    No Known Activations