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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    י
    0.97
    abhavam
    0.93
    ৬
    0.92
    कल
    0.88
     וע
    0.82
    ্ু
    0.82
    akaranam
    0.79
    所以在
    0.79
    מי
    0.78
    所以我
    0.77
    POSITIVE LOGITS
    ђу
    0.80
     oblig
    0.76
    shells
    0.74
    flows
    0.73
     मांगी
    0.71
    Beware
    0.70
     анализа
    0.68
     Δια
    0.68
     multiplic
    0.68
     omn
    0.65
    Act Density 0.001%

    No Known Activations