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

    Neuronpedia

    INDEX
    Explanations

    Named entities and ascending order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Batis
    -0.63
    ed
    -0.59
     publiques
    -0.59
     enfans
    -0.58
    azar
    -0.57
     efeito
    -0.56
     pregunto
    -0.55
     avoient
    -0.54
     pubblici
    -0.54
     consommateurs
    -0.54
    POSITIVE LOGITS
    ScopeManager
    0.63
    ChildScrollView
    0.60
    aarrggbb
    0.58
    liziert
    0.57
    writeFieldEnd
    0.57
    ContentAsync
    0.56
    MigrationBuilder
    0.56
     виправивши
    0.56
     Moul
    0.54
    anias
    0.53
    Act Density 0.084%

    No Known Activations