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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LowerCase
    0.89
     codecs
    0.86
     remembr
    0.86
    ierungen
    0.84
    ure
    0.83
    Ranges
    0.82
    𝖊
    0.82
    ierung
    0.82
    centric
    0.79
     terminate
    0.79
    POSITIVE LOGITS
    х
    0.90
    д
    0.90
    м
    0.89
     Жен
    0.89
    య్యా
    0.88
    𝗴
    0.86
    า
    0.85
    нди
    0.84
    Estr
    0.84
    ../
    0.83
    Act Density 0.014%

    No Known Activations