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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mafia
    0.45
    ravi
    0.41
     Temmuz
    0.40
     Nasir
    0.40
    سمى
    0.40
    俸
    0.40
     risposta
    0.40
     Renaissance
    0.39
    බා
    0.38
    ipal
    0.38
    POSITIVE LOGITS
    élim
    0.46
     hướng
    0.43
    տն
    0.41
    eylon
    0.40
    里程
    0.39
    ый
    0.38
     upped
    0.37
    娉
    0.36
     가정
    0.35
    摒
    0.35
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.