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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Manhattan
    0.51
     Philadelphia
    0.48
     Brooklyn
    0.48
     NYU
    0.45
     Cadillac
    0.45
     downtown
    0.44
     transatlantic
    0.43
     Midtown
    0.43
     Westchester
    0.43
     Gotham
    0.42
    POSITIVE LOGITS
    鲷
    0.42
     agric
    0.42
     modifica
    0.42
     туристи
    0.41
     fecha
    0.40
    로그
    0.40
    瞍
    0.40
     сельскохозяй
    0.40
     Gron
    0.40
    ագր
    0.39
    Act Density 0.007%

    No Known Activations