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

    Neuronpedia

    INDEX
    Explanations

    she/her/woman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    0.88
     koji
    0.84
     який
    0.79
     ktorý
    0.75
     који
    0.75
     který
    0.74
     نفسه
    0.73
     который
    0.71
     sám
    0.71
     attivo
    0.71
    POSITIVE LOGITS
     herself
    1.55
     которая
    1.11
     نفسها
    1.07
     која
    1.06
     koja
    0.98
     решила
    0.97
     ktorá
    0.96
     должна
    0.95
     която
    0.95
     કરવું
    0.95
    Act Density 0.020%

    No Known Activations