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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     assuming
    0.45
     valor
    0.43
     ventures
    0.42
     momentarily
    0.40
     infrastructure
    0.39
    读
    0.39
     read
    0.39
    眉
    0.39
     hin
    0.39
     used
    0.39
    POSITIVE LOGITS
    ionat
    0.42
    𠄌
    0.41
    tyn
    0.41
    га
    0.39
    셩
    0.39
    ρέ
    0.39
    asku
    0.39
     décembre
    0.38
    ഗ്യ
    0.38
    നിമ
    0.38
    Act Density 0.000%

    No Known Activations