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

    Neuronpedia

    INDEX
    Explanations

    your and yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பொதுவாக
    0.49
    基本的に
    0.46
    頗
    0.46
     eup
    0.44
     corpses
    0.43
     कथित
    0.41
     principalement
    0.41
     பெரும்பாலும்
    0.41
     idiosync
    0.41
     Mathematik
    0.41
    POSITIVE LOGITS
     YOUR
    0.79
     your
    0.79
     Your
    0.66
     votre
    0.63
     YOU
    0.61
    Your
    0.60
    你的
    0.60
     vaše
    0.59
     আপনার
    0.58
     você
    0.57
    Act Density 0.170%

    No Known Activations