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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lifeboat
    0.53
    ardino
    0.48
    蛋白质
    0.47
    нів
    0.46
     Greenberg
    0.46
    ონი
    0.46
    <0xB1>
    0.45
     preservation
    0.45
    ędzy
    0.45
    렛
    0.45
    POSITIVE LOGITS
     ilgi
    0.51
    evil
    0.49
     succesfully
    0.48
    ’
    0.48
    IDE
    0.48
    ה
    0.47
     une
    0.44
     la
    0.44
    HC
    0.44
     ໃນ
    0.44
    Act Density 0.000%

    No Known Activations