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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    三个
    -0.08
    Detection
    -0.07
     Hol
    -0.07
     accomplishments
    -0.06
     XCTAssert
    -0.06
     longitud
    -0.06
     expired
    -0.06
     masking
    -0.06
     liquids
    -0.06
    .visible
    -0.06
    POSITIVE LOGITS
    ERN
    0.08
    ا�
    0.07
    trained
    0.07
    ीड
    0.07
    .MAIN
    0.07
    яем
    0.07
    rai
    0.06
    724
    0.06
    カード
    0.06
    ständ
    0.06
    Act Density 0.001%

    No Known Activations