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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    où
    0.42
    IRY
    0.42
    郑
    0.40
    🇯
    0.40
    জিট
    0.40
    Sof
    0.38
    🧚
    0.38
    PMorgan
    0.38
    藓
    0.38
     intu
    0.37
    POSITIVE LOGITS
     captive
    0.41
     আশ্রয়
    0.41
     ประจํา
    0.41
     prevailing
    0.40
     occupies
    0.40
    व्र
    0.40
     sanciones
    0.40
     alcun
    0.40
    ៈ
    0.39
     受け
    0.39
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.