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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commercial
    -0.10
     фам
    -0.08
     commercially
    -0.08
    commercial
    -0.07
     কে
    -0.07
     multiplic
    -0.07
    .apache
    -0.07
     kidney
    -0.07
     Tudor
    -0.07
    商业
    -0.07
    POSITIVE LOGITS
     vantage
    0.12
     atop
    0.11
     climbed
    0.11
     올라
    0.11
     hikes
    0.11
     sommet
    0.11
     верш
    0.11
     exhilar
    0.11
     pinnacle
    0.10
     hills
    0.10
    Act Density 0.045%

    No Known Activations