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
     himself
    1.02
     그는
    0.92
    彼は
    0.89
     نفسه
    0.85
     അദ്ദേഹം
    0.81
     jego
    0.78
    他的
    0.77
     his
    0.76
     เขา
    0.75
    his
    0.75
    POSITIVE LOGITS
     herself
    2.27
    她的
    1.33
     نفسها
    1.31
    彼女
    1.30
     그녀
    1.27
     her
    1.26
     miała
    1.26
     acompañada
    1.25
    她
    1.23
     she
    1.22
    Act Density 0.021%

    No Known Activations