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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RANDOM
    -0.07
    ampling
    -0.07
    -analytics
    -0.07
     경제
    -0.06
    occupied
    -0.06
    WebService
    -0.06
     args
    -0.06
    -------
    -0.06
    _penalty
    -0.06
    _employee
    -0.06
    POSITIVE LOGITS
     }}">
    0.08
     výbě
    0.07
     хочу
    0.07
     XCTAssertTrue
    0.06
    dain
    0.06
    Một
    0.06
    IEnumerable
    0.06
    臺
    0.06
     Neue
    0.06
     Kens
    0.06
    Act Density 0.225%

    No Known Activations