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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    禍
    0.52
     Writings
    0.52
     Geschwindigkeit
    0.51
    uque
    0.50
    我們
    0.49
    <0xB7>
    0.49
     Франции
    0.49
    framed
    0.48
    堝
    0.47
    жие
    0.47
    POSITIVE LOGITS
     ساح
    0.46
     studio
    0.46
     upset
    0.44
     auto
    0.44
     accent
    0.43
    ↵↵
    0.42
     playa
    0.41
    insley
    0.41
     taka
    0.40
     תק
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.