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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isPlaying
    1.20
     punishments
    1.17
    ು
    1.15
    ല
    1.15
     pö
    1.14
     одежды
    1.14
     внимания
    1.14
     zealand
    1.12
    স
    1.12
    телно
    1.10
    POSITIVE LOGITS
     '',
    1.22
    BufOffset
    1.17
    কারের
    1.17
    !='
    1.16
    $\--
    1.14
    ciencia
    1.10
     '')
    1.10
     "'"
    1.09
    ुत
    1.09
    -\
    1.08
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.