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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ρικ
    0.48
     Enseñanza
    0.45
    笪
    0.45
    睇
    0.43
    רו
    0.43
    懼
    0.42
     Ausstellung
    0.42
    rogation
    0.41
     pengaruh
    0.41
    افيه
    0.40
    POSITIVE LOGITS
    见
    0.41
     fin
    0.40
    ä
    0.40
     details
    0.38
     surely
    0.38
     diver
    0.38
    Id
    0.37
     is
    0.37
    ax
    0.37
     const
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.