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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	unit
    -0.07
     compl
    -0.07
     trumpet
    -0.07
     *"
    -0.07
    	com
    -0.07
     requested
    -0.07
    .public
    -0.07
    .↵
    -0.07
     postponed
    -0.06
     ‎#
    -0.06
    POSITIVE LOGITS
     Sử
    0.06
     Αθή
    0.06
     ligne
    0.06
    원
    0.06
    ування
    0.06
    den
    0.06
     además
    0.06
    Tip
    0.06
    up
    0.06
    ドラ
    0.06
    Act Density 0.228%

    No Known Activations