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

    Neuronpedia

    INDEX
    Explanations

    future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     articles
    -0.07
     NORMAL
    -0.07
    産
    -0.07
    letics
    -0.06
     lệnh
    -0.06
    يمة
    -0.06
    redentials
    -0.06
    �
    -0.06
    Anyway
    -0.06
    cripts
    -0.06
    POSITIVE LOGITS
     genie
    0.07
    (..
    0.06
    úc
    0.06
     And
    0.06
     ไทย
    0.06
     Frankfurt
    0.06
    	true
    0.06
    (Spring
    0.06
    .Annotation
    0.06
     midd
    0.06
    Act Density 0.011%

    No Known Activations