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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hout
    0.99
    Miller
    0.98
    oselect
    0.98
    лдуу
    0.95
    onas
    0.94
     planilla
    0.94
    摳
    0.92
    Decision
    0.91
    Nullable
    0.91
    t
    0.90
    POSITIVE LOGITS
     অক্সিজ
    0.95
    벅
    0.94
     Increase
    0.92
    一個
    0.91
     στην
    0.90
     μεγά
    0.89
     大き
    0.89
     என்ற
    0.89
     Periods
    0.88
     einer
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.