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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不但
    0.45
    _{
    0.41
     مسلح
    0.40
    bordered
    0.39
     teaming
    0.38
     मनुष्य
    0.38
     beho
    0.38
    owed
    0.38
     Investigative
    0.38
    ^{
    0.36
    POSITIVE LOGITS
    리
    0.58
    யில்
    0.51
    ETTE
    0.50
    REY
    0.47
     longue
    0.45
    ٹری
    0.45
    𝗘
    0.45
    대
    0.44
     singleRun
    0.44
     fórm
    0.44
    Act Density 0.001%

    No Known Activations