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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ers
    1.13
    ERS
    1.02
    WS
    0.95
    pathy
    0.94
    彼は
    0.93
    pat
    0.91
    ने
    0.88
    rake
    0.86
    க
    0.83
    ographer
    0.82
    POSITIVE LOGITS
     utilizzato
    1.45
     échant
    1.41
    ी
    1.34
     incompl
    1.31
    erent
    1.30
     Insgesamt
    1.28
    颖
    1.27
     abbastanza
    1.26
     பயன்படுத்த
    1.24
     bahwa
    1.24
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.