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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    雖然
    0.62
     deple
    0.59
     aspetto
    0.58
     ******
    0.57
     depreci
    0.57
    虽然
    0.56
     비롯
    0.55
     sawa
    0.55
     onus
    0.55
    niveau
    0.54
    POSITIVE LOGITS
    ↵↵
    0.73
    ↵
    0.67
    enroll
    0.65
     Executive
    0.63
     Congressman
    0.63
     Biographical
    0.63
     Él
    0.61
    </h3>
    0.61
    </h1>
    0.60
    <0xE2>
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.