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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mau
    0.49
     everyone
    0.47
     blood
    0.45
     People
    0.45
     tek
    0.45
     whole
    0.44
     jemand
    0.43
     is
    0.42
     mira
    0.42
     tad
    0.42
    POSITIVE LOGITS
    ๚
    0.78
    ↵↵↵
    0.77
    agę
    0.73
     interstitiis
    0.72
    nommen
    0.72
    ನ್ನು
    0.71
    ↵↵↵↵
    0.71
    ↵↵
    0.67
    ↵↵↵↵↵
    0.67
    iają
    0.66
    Act Density 0.998%

    No Known Activations