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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     сосед
    -0.08
    root
    -0.08
    出会
    -0.08
     Meer
    -0.07
     a
    -0.07
    (AdapterView
    -0.07
    vell
    -0.07
    router
    -0.07
    	Address
    -0.07
    illion
    -0.07
    POSITIVE LOGITS
     lesbians
    0.07
    🏛
    0.07
    检察官
    0.07
     dù
    0.07
     Czech
    0.07
     ông
    0.07
     декаб
    0.07
     psychiat
    0.06
    癃
    0.06
    ؤول
    0.06
    Act Density 0.005%

    No Known Activations