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

    Neuronpedia

    INDEX
    Explanations

    backtick

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    鹑
    -0.07
    约会
    -0.07
     Emm
    -0.07
    ܉
    -0.07
    silver
    -0.07
     Sta
    -0.06
    Ale
    -0.06
    Tra
    -0.06
     swords
    -0.06
    POSITIVE LOGITS
     Pound
    0.08
     tahun
    0.07
    🖱
    0.07
    ROW
    0.07
    ói
    0.07
    (prediction
    0.07
    .persistent
    0.07
    	p
    0.07
    在网上
    0.06
    uhn
    0.06
    Act Density 0.016%

    No Known Activations