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

    Neuronpedia

    INDEX
    Explanations

    announcements, new initiatives, or changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     همان
    0.72
     either
    0.71
     เหมือน
    0.71
     existe
    0.69
     conocemos
    0.68
     quintessential
    0.67
     evidente
    0.65
     crucible
    0.65
    라이언트
    0.64
     consummate
    0.64
    POSITIVE LOGITS
     новый
    0.88
     ಹೊಸ
    0.87
    新的
    0.86
     để
    0.85
     новых
    0.84
     nuevas
    0.82
    を発表
    0.79
     neuen
    0.79
     nuevos
    0.79
     nuovi
    0.79
    Act Density 0.095%

    No Known Activations