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

    Neuronpedia

    INDEX
    Explanations

    words starting with Re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    적으로
    0.41
    赅
    0.40
    殳
    0.38
    ర్వాత
    0.37
     внутрен
    0.37
    того
    0.37
    钀
    0.36
    荣誉
    0.35
    mL
    0.35
     বদলে
    0.35
    POSITIVE LOGITS
     Re
    0.77
    Re
    0.68
    jection
    0.62
    becca
    0.61
    ponse
    0.58
     RE
    0.58
     re
    0.56
    ources
    0.54
    versible
    0.54
    aching
    0.53
    Act Density 0.121%

    No Known Activations