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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     coming
    0.72
     in
    0.71
    ו
    0.71
     particuliers
    0.68
     inwards
    0.68
     wrappers
    0.67
    нің
    0.67
     sooner
    0.65
     येणार
    0.64
    编码
    0.64
    POSITIVE LOGITS
     الل
    1.07
     Ла
    1.05
     Л
    1.05
     Lars
    1.04
     Ф
    1.00
     LR
    1.00
     Но
    0.99
     Да
    0.99
     LK
    0.96
     Tact
    0.95
    Act Density 0.000%

    No Known Activations