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

    Neuronpedia

    INDEX
    Explanations

    places, estates, and leisure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    2.20
    s
    1.87
    the
    1.64
    2
    1.64
    1
    1.62
    an
    1.59
    land
    1.59
    al
    1.48
    line
    1.44
    list
    1.43
    POSITIVE LOGITS
    та
    1.56
    م
    1.55
    મ
    1.54
     estadísticas
    1.52
    い
    1.51
    ম
    1.41
     científ
    1.41
     bạn
    1.35
    abı
    1.35
    프
    1.34
    Act Density 0.050%

    No Known Activations