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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    鍋
    0.50
    珢
    0.49
    льній
    0.46
    』（
    0.44
    耺
    0.44
     Liquor
    0.42
    🌰
    0.42
    เค
    0.41
    כת
    0.41
    🥚
    0.41
    POSITIVE LOGITS
     zwe
    0.53
     traumat
    0.52
     saludables
    0.48
     lima
    0.48
     zawod
    0.47
     vieux
    0.47
     aplicado
    0.47
     usadas
    0.47
     COMMITTEE
    0.46
     jardin
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.