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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ायन
    -0.07
    .Localization
    -0.06
    арч
    -0.06
    σιεύ
    -0.06
    _STOCK
    -0.06
    "
↵
↵
↵
    -0.06
    Ellipse
    -0.06
    umd
    -0.06
    ैठ
    -0.06
    .AddTransient
    -0.06
    POSITIVE LOGITS
    相信
    0.07
    serv
    0.07
    bcm
    0.07
    知道
    0.07
     Meetings
    0.07
     focused
    0.06
     nemůže
    0.06
     pals
    0.06
    	find
    0.06
     Rupert
    0.06
    Act Density 0.020%

    No Known Activations