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

    Neuronpedia

    INDEX
    Explanations

    actions performed by himself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    your
    0.64
     yourselves
    0.63
     your
    0.61
    Your
    0.57
     yourself
    0.56
     him
    0.55
     lui
    0.53
     iyong
    0.53
    彼
    0.53
    yourself
    0.52
    POSITIVE LOGITS
     himself
    1.48
     తన
    1.16
     തന്റെ
    1.13
     نفسه
    1.00
     his
    0.97
     Himself
    0.93
     자신의
    0.92
     தனது
    0.92
     ತನ್ನ
    0.86
     своему
    0.83
    Act Density 0.015%

    No Known Activations