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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    residents
    0.39
    shard
    0.39
    ś
    0.39
     Neighbor
    0.38
    Shard
    0.38
    Sh
    0.38
    马
    0.38
    usi
    0.38
    シャ
    0.38
     vå
    0.37
    POSITIVE LOGITS
    ллина
    0.39
     rescind
    0.39
     biographical
    0.38
     ||=
    0.37
    氚
    0.37
    പ്പി
    0.37
     ликви
    0.37
     сви
    0.36
     glycerin
    0.36
    会計
    0.36
    Act Density 0.000%

    No Known Activations