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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rv
    0.44
    mány
    0.44
    㐄
    0.42
    ]$,
    0.40
    運動
    0.40
    кин
    0.40
    ટ
    0.40
    ]}{
    0.39
    致力
    0.39
     移動
    0.39
    POSITIVE LOGITS
     flashbacks
    0.49
     ils
    0.48
     nostalgia
    0.47
     licenses
    0.46
     increment
    0.44
     partitions
    0.44
     permiss
    0.44
     pier
    0.44
     permit
    0.43
     throat
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.