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

    Neuronpedia

    INDEX
    Explanations

    over the Internet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    秦
    0.40
     прой
    0.38
    speople
    0.37
    shaw
    0.35
    ogue
    0.34
     फलस्वरूप
    0.34
    েকে
    0.34
     வி
    0.34
     reaping
    0.34
    Luis
    0.34
    POSITIVE LOGITS
     ندارد
    0.41
     ně
    0.41
    ецца
    0.40
     نیست
    0.40
     manifolds
    0.39
    但在
    0.39
    이지만
    0.39
     nodos
    0.38
     н
    0.38
     específica
    0.38
    Act Density 0.001%

    No Known Activations