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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ayat
    0.97
     sofá
    0.88
    ト
    0.88
     térmica
    0.87
     trays
    0.86
     sdx
    0.85
     sofa
    0.84
     alignItems
    0.84
     hooks
    0.84
    发放
    0.84
    POSITIVE LOGITS
     воз
    0.72
    сторон
    0.71
    jenkins
    0.66
    ohr
    0.65
    oll
    0.63
     renversement
    0.62
    waż
    0.61
    篇
    0.61
    Retrie
    0.61
    oui
    0.61
    Act Density 0.000%

    No Known Activations