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

    Neuronpedia

    INDEX
    Explanations

    reducing support, manual effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    йл
    0.50
    富有
    0.47
    庸
    0.47
    കാന്‍
    0.45
     দিচ্ছে
    0.44
    外国
    0.44
    Chào
    0.43
    LOUISE
    0.43
     fenô
    0.43
     приветствовать
    0.43
    POSITIVE LOGITS
     you
    0.52
     of
    0.51
     )
    0.51
     that
    0.50
     to
    0.49
     this
    0.49
     immediately
    0.48
     stages
    0.47
     {
    0.46
     allegedly
    0.46
    Act Density 0.003%

    No Known Activations