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

    Neuronpedia

    INDEX
    Explanations

    поп

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hard
    -0.07
    คว
    -0.07
    حی
    -0.06
    แต
    -0.06
    ména
    -0.06
    -re
    -0.06
    ρυ
    -0.06
     stain
    -0.06
    gu
    -0.06
    iyatı
    -0.06
    POSITIVE LOGITS
     поп
    0.34
     Поп
    0.14
     потрап
    0.12
     попада
    0.08
     testament
    0.08
    陆
    0.08
     làn
    0.06
     Ник
    0.06
     Aleppo
    0.06
     mainstream
    0.06
    Act Density 0.001%

    No Known Activations