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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     uang
    0.89
     ethnographic
    0.75
     hamburgers
    0.75
     provinsi
    0.74
     avert
    0.73
     objekt
    0.73
     nationalists
    0.73
    dater
    0.72
    藝術
    0.72
     phospholipids
    0.72
    POSITIVE LOGITS
    *}$
    0.74
     최종
    0.74
     Combining
    0.72
     mohabbat
    0.72
    ่
    0.72
     splitting
    0.71
    স
    0.71
    அல்ல
    0.70
    *((*
    0.70
    তে
    0.70
    Act Density 0.002%

    No Known Activations