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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ادى
    0.77
    ור
    0.76
    ่ง
    0.75
    ogical
    0.74
    藺
    0.74
    <unused42>
    0.72
    ependence
    0.71
    س
    0.71
     Flight
    0.71
    簹
    0.71
    POSITIVE LOGITS
     pedibus
    0.71
     novem
    0.66
     sparsim
    0.66
     perspici
    0.65
     gøre
    0.64
    ፩
    0.64
    official
    0.64
    सनीय
    0.64
     ricevere
    0.64
    യുടെ
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.