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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .For
    -0.07
    '|
    -0.07
     Vers
    -0.07
    .Caption
    -0.07
     vice
    -0.06
     oud
    -0.06
    首席
    -0.06
     Ast
    -0.06
    edicine
    -0.06
    >{$
    -0.06
    POSITIVE LOGITS
    QA
    0.08
    _QU
    0.07
    hoff
    0.07
    غل
    0.07
     Physiology
    0.07
    ཧ
    0.07
    汚
    0.07
    fähig
    0.07
     XCTAssertEqual
    0.07
    -ground
    0.07
    Act Density 0.004%

    No Known Activations