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

    Neuronpedia

    INDEX
    Explanations

    Chang Jiang or Loveisrespect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모
    0.70
     Stops
    0.67
     நாய
    0.67
    峥
    0.67
     பதில
    0.66
    OV
    0.66
     जनप्रतिनि
    0.65
     responsive
    0.65
     NEX
    0.64
     क्लाइ
    0.64
    POSITIVE LOGITS
    non
    0.78
    Non
    0.71
     non
    0.68
     Bath
    0.68
     নন
    0.67
     Ins
    0.65
     Non
    0.64
    ome
    0.63
    insen
    0.62
    非
    0.62
    Act Density 0.017%

    No Known Activations