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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    题
    -0.08
    辩
    -0.07
    üst
    -0.07
    ction
    -0.07
    ARIO
    -0.07
    turn
    -0.07
     review
    -0.06
    찿
    -0.06
    鬥
    -0.06
     rehearsal
    -0.06
    POSITIVE LOGITS
    湖州
    0.07
    👈
    0.07
     UserController
    0.07
    	MPI
    0.07
    מב
    0.07
     يمكنك
    0.07
     APA
    0.07
     appellate
    0.07
    .getDefault
    0.07
    全国各地
    0.07
    Act Density 0.001%

    No Known Activations