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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ium
    0.48
     क्रमा
    0.46
    Connections
    0.46
     دستیاب
    0.45
    Retention
    0.43
     باتیں
    0.40
     Available
    0.40
    Available
    0.39
     Retention
    0.39
     retention
    0.38
    POSITIVE LOGITS
    adorable
    0.43
    股
    0.41
     revolutionize
    0.40
     basaltes
    0.39
     podat
    0.39
    흑
    0.39
    אים
    0.39
    aje
    0.38
     embodies
    0.38
     δικ
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.