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

    Neuronpedia

    INDEX
    Explanations

    ไซไฟ, แชร์, เมล็ด

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     égales
    0.85
    łącznie
    0.82
     од
    0.74
    ódigo
    0.72
     pune
    0.70
    ﺎ
    0.68
    đ
    0.68
    ulp
    0.67
    ífica
    0.67
     ayrıca
    0.66
    POSITIVE LOGITS
     Somehow
    0.80
     Leach
    0.78
     Guan
    0.75
     Boo
    0.74
     findest
    0.74
    pillar
    0.73
    Basel
    0.73
     Granny
    0.73
     TripAdvisor
    0.73
     outperforms
    0.72
    Act Density 0.016%

    No Known Activations