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

    Neuronpedia

    INDEX
    Explanations

    groups of people/society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.59
     touristes
    -0.56
     незавершена
    -0.50
     citoyens
    -0.49
     autorités
    -0.49
     bénévoles
    -0.48
    DrawerToggle
    -0.48
    wszy
    -0.47
    GEBURTS
    -0.47
     lecteurs
    -0.47
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.61
    cences
    0.56
     bindings
    0.56
    TProtocol
    0.56
    LookAnd
    0.55
     and
    0.55
     ThemeData
    0.55
     reducers
    0.54
     rules
    0.54
     wheels
    0.54
    Act Density 0.001%

    No Known Activations