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

    Neuronpedia

    INDEX
    Explanations

    rumors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fection
    -0.07
    />";↵
    -0.07
     свят
    -0.07
    .setScene
    -0.07
    iance
    -0.07
    اء
    -0.06
     درجة
    -0.06
     приготовить
    -0.06
     adaptation
    -0.06
     براى
    -0.06
    POSITIVE LOGITS
     rumors
    0.12
     rumored
    0.12
     rumor
    0.11
     rumours
    0.09
     rum
    0.09
     Rum
    0.08
    reviews
    0.07
    Sql
    0.07
    shop
    0.06
     Learned
    0.06
    Act Density 0.005%

    No Known Activations