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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     adimensional
    0.47
     stripos
    0.46
    Ĺ
    0.45
     queremos
    0.44
    伢
    0.43
     смер
    0.43
    閆
    0.43
     гаран
    0.42
    習慣
    0.42
    ディング
    0.42
    POSITIVE LOGITS
    urados
    0.44
    ains
    0.41
    ⋙
    0.40
    nucle
    0.39
    aphor
    0.39
     battles
    0.39
    rounded
    0.39
     voisins
    0.38
     territories
    0.38
    پار
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.