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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ágot
    0.71
     退
    0.70
     &
    0.68
     وع
    0.67
    ྒྱ
    0.65
     foc
    0.65
     निरीक्षण
    0.65
     🌱
    0.64
     זו
    0.64
       
    0.63
    POSITIVE LOGITS
    脨
    0.85
    ﮯ
    0.83
    stylesheets
    0.80
    redients
    0.79
    <unused558>
    0.79
    thisobject
    0.78
     sämt
    0.77
     لاءِ
    0.75
    تد
    0.75
    tiles
    0.75
    Act Density 0.000%

    No Known Activations