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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     госп
    -0.06
    ्यवस
    -0.06
    θρώ
    -0.06
     Force
    -0.06
    Areas
    -0.06
     modes
    -0.06
     dohod
    -0.06
     kra
    -0.06
     Kra
    -0.06
     corpor
    -0.06
    POSITIVE LOGITS
     translation
    0.08
    translation
    0.07
     піз
    0.07
     instantly
    0.07
    】
    0.07
    Translation
    0.06
    寶
    0.06
    입니다
    0.06
     Deutsch
    0.06
    tesy
    0.06
    Act Density 0.021%

    No Known Activations