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

    Neuronpedia

    INDEX
    Explanations

    a plan to search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %
    0.46
    :
    0.44
     no
    0.43
     buenos
    0.42
     ellas
    0.41
     Tierra
    0.41
    [
    0.41
    May
    0.40
     terceros
    0.40
     roam
    0.40
    POSITIVE LOGITS
    erweise
    0.52
    صیلی
    0.51
    ىن
    0.50
    atir
    0.49
    etten
    0.48
    リ
    0.47
    িগ
    0.46
    ällt
    0.46
    ิลป
    0.46
    ابقة
    0.46
    Act Density 0.002%

    No Known Activations