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

    Neuronpedia

    INDEX
    Explanations

    evolving, changing, shifting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    0.80
    它
    0.80
     ﺍﻟ
    0.79
     և
    0.77
    يل
    0.76
    ال
    0.75
     paralyzed
    0.75
    사
    0.74
     inundated
    0.73
    0.72
    POSITIVE LOGITS
    -
    1.09
    ing
    1.04
    a
    1.01
    .
    0.88
    ly
    0.87
    o
    0.86
    ة
    0.86
    ING
    0.82
    EST
    0.73
    aS
    0.72
    Act Density 0.149%

    No Known Activations