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

    Neuronpedia

    INDEX
    Explanations

    research articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sheet
    -0.07
    暗暗
    -0.07
    ła
    -0.07
     typ
    -0.07
    swith
    -0.07
     crawled
    -0.07
     +:+
    -0.06
     Đồng
    -0.06
     Share
    -0.06
    сы
    -0.06
    POSITIVE LOGITS
     대부분
    0.07
     astonishing
    0.07
     WA
    0.07
    APO
    0.07
    otomy
    0.07
     우리나라
    0.07
     Communications
    0.06
    مواق
    0.06
    _reference
    0.06
     Morocco
    0.06
    Act Density 0.017%

    No Known Activations