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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Approved
    -0.07
    	MPI
    -0.07
    暶
    -0.07
    北斗
    -0.07
    called
    -0.07
    (orig
    -0.07
    ensive
    -0.07
     waved
    -0.07
    ►
    -0.07
    erging
    -0.07
    POSITIVE LOGITS
    ब
    0.08
    テ
    0.07
    实
    0.07
    人都
    0.07
     lowercase
    0.07
     digit
    0.07
     rahatsız
    0.07
    _guest
    0.07
    क
    0.07
    issement
    0.07
    Act Density 0.008%

    No Known Activations