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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ING
    1.02
     licensure
    0.99
     manners
    0.96
    locks
    0.96
     corporations
    0.95
     Trou
    0.93
    릭터
    0.93
     rooftops
    0.92
    ITECTURE
    0.91
     conduits
    0.91
    POSITIVE LOGITS
    ل
    1.86
    ور
    1.59
    ır
    1.52
     është
    1.45
     này
    1.43
    ük
    1.43
    in
    1.38
    el
    1.35
    ר
    1.35
    ão
    1.34
    Act Density 0.829%

    No Known Activations