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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Quân
    0.43
    ignes
    0.42
    çalves
    0.41
    Treatment
    0.41
    運営
    0.41
     Equipo
    0.40
    Heute
    0.40
    <unused61>
    0.39
    tool
    0.39
    Ross
    0.39
    POSITIVE LOGITS
     syllables
    0.52
    𝙪
    0.47
     attacks
    0.47
     protocols
    0.47
     liberties
    0.46
     inflows
    0.46
     февра
    0.46
     보호
    0.45
     tī
    0.44
     imperatives
    0.44
    Act Density 0.006%

    No Known Activations