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

    Neuronpedia

    INDEX
    Explanations

    purpose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     до
    -0.06
    逸
    -0.06
    stderr
    -0.06
    	payload
    -0.06
     certify
    -0.06
    中文字幕
    -0.06
    ampp
    -0.06
     bilm
    -0.06
     ofrec
    -0.06
    -stop
    -0.06
    POSITIVE LOGITS
     свет
    0.07
    .Network
    0.06
    !");↵
    0.06
    /control
    0.06
    istical
    0.06
     toddler
    0.06
     Innovative
    0.06
    _visited
    0.06
    rad
    0.06
     квітня
    0.06
    Act Density 0.044%

    No Known Activations