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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     абсолютно
    0.68
    produksi
    0.60
     മനുഷ്യ
    0.59
    legal
    0.59
     miejscu
    0.58
    ї
    0.57
    seamless
    0.57
    adihi
    0.57
    annya
    0.56
     オフィス
    0.56
    POSITIVE LOGITS
     reverse
    0.60
     benzoic
    0.60
     reversals
    0.59
     Parsing
    0.59
     второй
    0.56
     Reverse
    0.56
     Pending
    0.55
     Scaling
    0.55
     Slight
    0.55
     conjectures
    0.55
    Act Density 11.687%

    No Known Activations