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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lock
    -0.41
     line
    -0.39
     thạch
    -0.38
     قرن
    -0.38
    ViewModels
    -0.38
     hole
    -0.38
     law
    -0.37
    aktur
    -0.37
    lock
    -0.36
    чно
    -0.36
    POSITIVE LOGITS
    CppMethod
    0.76
     MainAxisSize
    0.75
    CloseOperation
    0.75
    IntoConstraints
    0.71
    gameserver
    0.70
     calendriers
    0.67
    apimachinery
    0.66
    +#+#
    0.65
     navideñas
    0.64
     thiệu
    0.63
    Act Density 0.003%

    No Known Activations