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

    Neuronpedia

    INDEX
    Explanations

    Liberty and Finance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Freedom
    -0.81
     vote
    -0.80
    Freedom
    -0.63
     Liberty
    -0.57
     FREEDOM
    -0.55
    freedom
    -0.54
    paramref
    -0.52
     Liberties
    -0.52
    /$',
    -0.51
    IBOutlet
    -0.49
    POSITIVE LOGITS
    
    0.77
    ing
    0.70
    +#+#
    0.70
     pinulongan
    0.62
    WireFormat
    0.59
    HasAnnotation
    0.58
     contextLoads
    0.57
    Personendaten
    0.57
    windowFixed
    0.56
    terness
    0.54
    Act Density 0.065%

    No Known Activations