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

    Neuronpedia

    INDEX
    Explanations

    his and him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     các
    0.46
     defendants
    0.44
     самих
    0.42
    ជាតិ
    0.41
     mga
    0.40
    Defendants
    0.40
     metrics
    0.40
     coupes
    0.40
     themselves
    0.40
     untuk
    0.40
    POSITIVE LOGITS
     him
    1.36
     его
    1.33
     그의
    1.29
     jego
    1.28
    彼の
    1.27
     honom
    1.15
     his
    1.14
    他的
    1.14
     அவரை
    1.12
     njegove
    1.12
    Act Density 0.116%

    No Known Activations