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

    Neuronpedia

    INDEX
    Explanations

    sorting/partitioning algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    解釋
    -0.07
    หมอ
    -0.07
    内饰
    -0.07
    nce
    -0.07
     Pills
    -0.07
    Han
    -0.07
    tems
    -0.06
    cen
    -0.06
     ambassador
    -0.06
    Context
    -0.06
    POSITIVE LOGITS
     cooperating
    0.08
     listening
    0.08
     STDOUT
    0.08
    	global
    0.07
    ביק
    0.07
    _IOC
    0.07
    燚
    0.07
    בצע
    0.07
    ϟ
    0.06
    讲话
    0.06
    Act Density 0.007%

    No Known Activations