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

    Neuronpedia

    INDEX
    Explanations

    flex;css display property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exceptionnelle
    0.67
     farmac
    0.66
     деву
    0.66
     jornalista
    0.65
    収納
    0.65
     ведь
    0.64
     サングラス
    0.64
     นาง
    0.64
     unwarranted
    0.63
    ៨
    0.63
    POSITIVE LOGITS
     जाऊन
    0.79
     have
    0.72
    겐
    0.70
     HAVE
    0.64
     get
    0.62
     quickest
    0.62
    WriteString
    0.62
    거
    0.62
     ints
    0.61
     ניתן
    0.61
    Act Density 0.020%

    No Known Activations