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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pregn
    -0.28
    æĺ¯ä¸Ģ
    -0.28
    ogene
    -0.26
    çļĦ强大
    -0.26
    åĺĽ
    -0.26
    辩
    -0.25
    urst
    -0.25
    enton
    -0.24
    _auc
    -0.24
    TeV
    -0.24
    POSITIVE LOGITS
    леÑĩ
    0.30
     chunk
    0.28
    anted
    0.26
     chunks
    0.25
    bulk
    0.25
    olvable
    0.25
    æī¹éĩı
    0.25
    allback
    0.24
    دÙĬØ©
    0.24
    olated
    0.24
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.