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

    Neuronpedia

    INDEX
    Explanations

    eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ire
    -0.08
     exception
    -0.07
    还有一些
    -0.07
     ян
    -0.07
     lam
    -0.07
    isAdmin
    -0.07
    nown
    -0.07
    过程当中
    -0.07
     contemplate
    -0.07
    .handleError
    -0.07
    POSITIVE LOGITS
    뼛
    0.08
     Polit
    0.07
    	mode
    0.07
     Bott
    0.06
    Hair
    0.06
    oji
    0.06
    ömür
    0.06
    ány
    0.06
     Hair
    0.06
    الي
    0.06
    Act Density 0.005%

    No Known Activations