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

    Neuronpedia

    INDEX
    Explanations

    code questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bathing
    -0.07
     เก
    -0.07
    /response
    -0.07
    22
    -0.06
     viewHolder
    -0.06
     物
    -0.06
     dob
    -0.06
    -db
    -0.06
     lokal
    -0.06
    31
    -0.06
    POSITIVE LOGITS
    isky
    0.07
    etail
    0.07
     Look
    0.07
     XCTAssertEqual
    0.07
    speaker
    0.06
    ?><?
    0.06
    Certainly
    0.06
    Shift
    0.06
     控
    0.06
    이나
    0.06
    Act Density 0.051%

    No Known Activations