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

    Neuronpedia

    INDEX
    Explanations

    respect towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     և
    0.50
     અને
    0.50
     poiché
    0.49
     प्रतिबिंब
    0.48
     अद्वितीय
    0.48
     și
    0.47
     و
    0.46
     ช่วย
    0.46
    姏
    0.46
     සහ
    0.45
    POSITIVE LOGITS
     members
    0.51
     operators
    0.51
     managers
    0.51
     players
    0.50
     workers
    0.50
     those
    0.49
     teachers
    0.48
     principles
    0.48
     actors
    0.47
     names
    0.46
    Act Density 0.002%

    No Known Activations