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

    Neuronpedia

    INDEX
    Explanations

    exam and examination contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     یا
    1.12
    漃
    1.02
     instal
    1.00
    iktok
    0.98
    見た
    0.98
     lesion
    0.96
     distinto
    0.95
    "/"
    0.95
     brune
    0.94
     なかっ
    0.94
    POSITIVE LOGITS
    ين
    1.75
    u
    1.29
    ме
    1.19
    ти
    1.16
    স
    1.11
    x
    1.06
    я
    1.05
    s
    1.03
    تي
    1.01
    ة
    0.98
    Act Density 0.007%

    No Known Activations