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

    Neuronpedia

    INDEX
    Explanations

    life and how it is lived

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ص
    0.43
    ك
    0.39
     م
    0.39
    ف
    0.39
    '
    0.39
    '،
    0.39
    ،
    0.39
     گ
    0.38
    الم
    0.38
    )،
    0.38
    POSITIVE LOGITS
    la
    0.36
    il
    0.34
    ar
    0.32
    at
    0.29
    ਿੰ
    0.29
    leneck
    0.29
    reciate
    0.29
    л
    0.28
     வாழ்க்கை
    0.28
    lar
    0.27
    Act Density 0.018%

    No Known Activations