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

    Neuronpedia

    INDEX
    Explanations

    yourself or myself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themselves
    1.02
     نفسه
    0.93
    自己
    0.93
     itself
    0.89
     خود
    0.89
    自分
    0.88
     himself
    0.87
     себе
    0.83
     خودش
    0.80
     نفسها
    0.80
    POSITIVE LOGITS
      
    0.49
     physically
    0.43
     ​​
    0.35
     professionally
    0.35
     accord
    0.34
    ishly
    0.34
     reen
    0.33
     adequately
    0.32
    த்தான
    0.32
     beğen
    0.32
    Act Density 0.142%

    No Known Activations