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

    Neuronpedia

    INDEX
    Explanations

    design/architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blessés
    -0.55
     enfans
    -0.54
     disponibilités
    -0.54
    hematics
    -0.53
    berdayakan
    -0.52
    nshaw
    -0.52
     rä
    -0.51
    velmente
    -0.51
     Immunology
    -0.49
    %</
    -0.49
    POSITIVE LOGITS
     BoxFit
    0.61
     समीक्षाओं
    0.59
    <bos>
    0.59
    rungsseite
    0.58
     statements
    0.57
    SuppressLint
    0.55
     незавершена
    0.54
     autorytatywna
    0.53
     forward
    0.52
     الاطلاع
    0.50
    Act Density 0.168%

    No Known Activations