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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arı
    0.51
     tact
    0.46
     хво
    0.46
     donor
    0.46
     cubed
    0.45
     wilt
    0.45
    し
    0.45
    ເພດ
    0.44
     দরকার
    0.44
     valeurs
    0.44
    POSITIVE LOGITS
    of
    0.59
    on
    0.53
    峈
    0.52
    olt
    0.51
    vorsch
    0.50
    Ordine
    0.50
     stöd
    0.50
    Brands
    0.50
     Stad
    0.49
    städter
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.