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

    Neuronpedia

    INDEX
    Explanations

    fragment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sowie
    -0.07
    高等院校
    -0.07
    时任
    -0.07
     fear
    -0.07
    ��
    -0.07
     truyền
    -0.06
     uso
    -0.06
    升温
    -0.06
     nguyên
    -0.06
     위치
    -0.06
    POSITIVE LOGITS
    .'));↵
    0.07
    Maria
    0.07
    ozo
    0.07
    📼
    0.06
    .piece
    0.06
    AccountId
    0.06
    controllers
    0.06
    бил
    0.06
    Flat
    0.06
    .animation
    0.06
    Act Density 0.001%

    No Known Activations