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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     elle
    1.10
     Elle
    1.06
     estuaries
    1.02
    Cyt
    0.95
    عه
    0.94
    merz
    0.94
    роки
    0.94
     lign
    0.93
     neoc
    0.92
     말고
    0.92
    POSITIVE LOGITS
     పథ
    1.26
    ,\,\,\,\
    1.11
    勮
    1.10
    வுடன்
    1.09
     וב
    1.09
    ために
    1.08
     суме
    1.08
    בער
    1.08
    ANSAS
    1.07
     खुशखबरी
    1.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.