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

    Neuronpedia

    INDEX
    Explanations

    strain or sprain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    1.06
    сы
    1.06
    ми
    1.04
    ческие
    1.02
    ста
    1.01
    skar
    0.93
    ০
    0.93
    ری
    0.93
    to
    0.90
    <0xBB>
    0.89
    POSITIVE LOGITS
    us
    1.57
     strains
    1.41
     be
    1.40
    ل
    1.38
    ن
    1.31
    o
    1.30
    ر
    1.21
     Strain
    1.17
     strain
    1.16
    a
    1.16
    Act Density 0.003%

    No Known Activations