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

    Neuronpedia

    INDEX
    Explanations

    spur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    1.53
    ように
    1.49
    ли
    1.42
     când
    1.41
     noastră
    1.31
    لي
    1.30
     maroc
    1.29
    1.28
     déchets
    1.26
     powied
    1.23
    POSITIVE LOGITS
    set
    1.15
    اد
    1.09
    1
    1.08
     I
    1.05
    sc
    1.02
    ุ
    1.02
    บ
    1.00
    "，
    0.98
    se
    0.97
     It
    0.96
    Act Density 0.000%

    No Known Activations