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

    Neuronpedia

    INDEX
    Explanations

    boolean true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     관련
    -0.07
    の方
    -0.07
     eigentlich
    -0.07
    售价
    -0.07
    ₑ
    -0.06
    �
    -0.06
    +offset
    -0.06
    왔다
    -0.06
     phrase
    -0.06
    (@
    -0.06
    POSITIVE LOGITS
    \Migrations
    0.07
     comunic
    0.07
     PIT
    0.07
    	meta
    0.07
    สอง
    0.07
     zmq
    0.07
     Hyde
    0.07
     umo
    0.07
     만
    0.07
    把它
    0.07
    Act Density 0.013%

    No Known Activations