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

    Neuronpedia

    INDEX
    Explanations

    ancient origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alang
    1.15
    edes
    1.14
    dering
    1.13
    ipy
    1.13
    iph
    1.13
     subst
    1.08
    ostic
    1.06
    ীকে
    1.05
    populated
    1.04
    toler
    1.03
    POSITIVE LOGITS
     tehát
    1.52
     dunque
    1.51
    그러나
    1.46
    Однако
    1.45
    といった
    1.42
    ちなみに
    1.38
     enfim
    1.35
     voltou
    1.34
     graças
    1.33
     inoltre
    1.33
    Act Density 0.180%

    No Known Activations