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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    illerie
    0.45
    ኒ
    0.38
    consciousness
    0.38
    numer
    0.38
    दायी
    0.38
    ⮕
    0.37
    faithful
    0.37
    ⴽ
    0.37
     हसन
    0.37
    тари
    0.36
    POSITIVE LOGITS
    charset
    0.39
     Wam
    0.38
     Vespa
    0.38
     trendy
    0.37
     Tables
    0.36
     contextual
    0.36
     geot
    0.36
     три
    0.36
     Crom
    0.36
    ाय
    0.36
    Act Density 0.002%

    No Known Activations