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

    Neuronpedia

    INDEX
    Explanations

    sequential numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eighty
    0.60
     ninety
    0.57
    の世界
    0.52
    ত্তর
    0.47
    ాతీయ
    0.46
    几十
    0.46
    ensk
    0.46
     seventy
    0.45
     Eighty
    0.44
    пла
    0.44
    POSITIVE LOGITS
     second
    0.95
     trzec
    0.90
     ketiga
    0.89
     zweiten
    0.89
     ikinci
    0.88
     második
    0.88
     الثالث
    0.88
     segunda
    0.87
     दूसरा
    0.87
     SECOND
    0.87
    Act Density 0.347%

    No Known Activations