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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bursting
    -0.07
     GFP
    -0.07
    英文
    -0.06
     XCTAssertEqual
    -0.06
    _tracker
    -0.06
     foo
    -0.06
     depos
    -0.06
     Lep
    -0.06
     Rever
    -0.06
     jo
    -0.06
    POSITIVE LOGITS
    cılar
    0.07
    Overall
    0.07
    ктів
    0.07
    ・━
    0.06
     اسلامی
    0.06
    abase
    0.06
     sẵn
    0.06
     متف
    0.06
    /pay
    0.06
    재
    0.06
    Act Density 0.005%

    No Known Activations