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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    त
    0.55
    ोनेशिया
    0.48
     있었습니다
    0.48
    España
    0.48
    ManagerProxy
    0.47
    浯
    0.46
    DataObject
    0.45
    aş
    0.44
     तला
    0.44
    亰
    0.44
    POSITIVE LOGITS
     be
    0.54
     pouring
    0.51
     consciously
    0.46
     mentally
    0.46
     bloating
    0.46
     picking
    0.45
     mesmer
    0.45
     constantly
    0.44
    вори
    0.44
     picked
    0.44
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.