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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     वर्त
    0.44
    after
    0.41
    赌
    0.40
     everyone
    0.38
    之后的
    0.37
     לאחר
    0.37
     위치
    0.37
     вр
    0.37
     हथ
    0.37
    enni
    0.37
    POSITIVE LOGITS
     ሽፋን
    0.43
     coverage
    0.41
    మంది
    0.40
    ឿ
    0.38
    GetResponse
    0.38
     prostu
    0.38
    親子
    0.37
    zust
    0.37
    အနေ
    0.37
    coverage
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.