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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    intă
    0.44
    ረሻ
    0.40
     남자
    0.39
    aient
    0.39
    Женско
    0.38
    cznych
    0.38
    ruari
    0.38
    americano
    0.38
    錄
    0.37
    Ini
    0.37
    POSITIVE LOGITS
     armes
    0.50
     Armed
    0.43
    Armed
    0.42
     armed
    0.41
     homogeneity
    0.40
     arm
    0.39
    enched
    0.39
     sz
    0.38
     arms
    0.38
    OnFile
    0.38
    Act Density 0.000%

    No Known Activations