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

    Neuronpedia

    INDEX
    Explanations

    depending on or improperly declared

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
               
    0.40
     conservation
    0.39
     ℝ
    0.39
    冉
    0.38
    w
    0.38
    ன்க
    0.37
     Reihen
    0.37
     apertures
    0.37
    '
    0.37
    缓
    0.37
    POSITIVE LOGITS
    EYER
    0.50
    FFEE
    0.47
    ೆಯೇ
    0.44
    Paf
    0.43
    EME
    0.43
     Westfield
    0.41
    ERRY
    0.41
    साय
    0.40
     finals
    0.40
    ÈME
    0.40
    Act Density 0.002%

    No Known Activations