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

    Neuronpedia

    INDEX
    Explanations

    respect and ethical behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     empêcher
    0.48
     চৈতন্যের
    0.46
     connaissez
    0.45
     championed
    0.42
     גר
    0.42
     আনন্দের
    0.41
     cleansed
    0.41
    ]::
    0.41
     થય
    0.41
     শতকরা
    0.41
    POSITIVE LOGITS
    Respect
    1.13
     Respect
    1.12
    respect
    1.11
     respekt
    1.08
     respect
    1.07
     RESPECT
    0.97
     respects
    0.90
     respe
    0.89
     respet
    0.86
     disrespect
    0.86
    Act Density 0.010%

    No Known Activations