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

    Neuronpedia

    INDEX
    Explanations

    Early Christian and Byzantine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idł
    0.40
    ንዱ
    0.38
     progresses
    0.37
    ிருந்தார்
    0.37
    否则
    0.36
     diced
    0.36
     мой
    0.36
    正好
    0.36
     број
    0.36
     माम
    0.35
    POSITIVE LOGITS
     sambil
    0.48
     navigation
    0.43
     नवीनतम
    0.43
    描き
    0.42
     tanpa
    0.39
    充滿
    0.39
     navigational
    0.38
    ونس
    0.38
     inspiring
    0.38
    深受
    0.37
    Act Density 0.003%

    No Known Activations