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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.46
    к
    0.45
     Types
    0.44
    liefer
    0.44
    werte
    0.43
    tores
    0.43
     Werte
    0.42
    ế
    0.42
    溫度
    0.41
    long
    0.41
    POSITIVE LOGITS
    0.52
    nox
    0.51
     easements
    0.50
     obsessed
    0.48
    ຢ່າງ
    0.48
     আর্ত
    0.47
    ısının
    0.47
    ພວກເຮ
    0.46
     possessed
    0.46
     appré
    0.46
    Act Density 0.000%

    No Known Activations