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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ciaux
    0.86
    afood
    0.84
    acés
    0.82
    Trailer
    0.80
    ➼
    0.77
     lontano
    0.76
     eserc
    0.76
    amanan
    0.75
    }})$
    0.75
     Север
    0.74
    POSITIVE LOGITS
    as
    0.80
     reckoning
    0.70
     collectible
    0.66
    ↵↵↵
    0.65
     лишь
    0.64
     dab
    0.64
     widow
    0.64
     contracting
    0.63
     mourning
    0.63
    으니
    0.63
    Act Density 0.002%

    No Known Activations