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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝑻
    0.84
    Ќ
    0.76
     منطقة
    0.72
     eficaz
    0.71
    podob
    0.71
    <unused32>
    0.70
     manera
    0.68
    Vida
    0.68
    puede
    0.68
    Przeczytaj
    0.68
    POSITIVE LOGITS
     and
    0.66
     refugee
    0.65
     (
    0.64
     did
    0.61
     &
    0.59
     cum
    0.59
     amd
    0.57
     barracks
    0.57
     were
    0.57
     monks
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.