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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Barbie
    0.54
     reducing
    0.51
     Reducing
    0.51
     lambs
    0.51
    न्त्री
    0.48
     residuals
    0.47
     technologists
    0.47
     residual
    0.47
     fennel
    0.46
     suppressing
    0.45
    POSITIVE LOGITS
    া
    0.54
    ા
    0.50
    туи
    0.50
    rzez
    0.48
     apare
    0.47
    勮
    0.47
    勬
    0.46
    N
    0.46
    仔细
    0.46
    ی
    0.45
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.