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

    Neuronpedia

    INDEX
    Explanations

    with from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imeInterval
    -0.06
    .he
    -0.06
    outed
    -0.06
     Clim
    -0.06
     ads
    -0.06
    .observable
    -0.06
     est
    -0.06
    변
    -0.06
    ��
    -0.06
     진
    -0.06
    POSITIVE LOGITS
     XCTAssert
    0.07
    -required
    0.07
     Reports
    0.07
    就是
    0.06
        ↵    ↵
    0.06
     uninsured
    0.06
    ーネ
    0.06
    .confirm
    0.06
     REPORT
    0.06
     elegance
    0.06
    Act Density 0.002%

    No Known Activations