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

    Neuronpedia

    INDEX
    Explanations

    brand-specific functional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plupart
    0.48
     букмекерлик
    0.45
    เภท
    0.40
     समस्त
    0.40
     niezbęd
    0.39
    国内外
    0.39
     rayonnement
    0.39
     प्रीवियस
    0.38
     pathophys
    0.38
    httparty
    0.38
    POSITIVE LOGITS
     menggunakan
    0.50
    ’
    0.49
     (
    0.47
     using
    0.46
     사용하는
    0.41
    -
    0.39
      
    0.38
    使用的是
    0.38
     via
    0.38
     from
    0.37
    Act Density 0.095%

    No Known Activations