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

    Neuronpedia

    INDEX
    Explanations

    first item or part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consecut
    1.06
     consecutive
    1.03
     successive
    0.99
     Consecutive
    0.94
     aikana
    0.81
    different
    0.79
     consecutively
    0.78
    きっと
    0.77
     között
    0.77
     φορά
    0.77
    POSITIVE LOGITS
    υ
    0.83
    engi
    0.80
    ей
    0.78
    ται
    0.77
    ímetros
    0.74
    ých
    0.73
     enterprise
    0.73
     두
    0.73
     १४
    0.73
     enterprises
    0.73
    Act Density 0.017%

    No Known Activations