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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     composite
    0.49
     necesitar
    0.49
     salary
    0.48
     ราคา
    0.47
     یا
    0.46
     น้ำ
    0.46
     costs
    0.44
    lar
    0.44
     lini
    0.44
     whey
    0.44
    POSITIVE LOGITS
    2
    0.47
    作者
    0.47
    0
    0.47
    9
    0.46
    口罩
    0.44
    5
    0.44
    சிரிய
    0.43
     výraz
    0.43
    мати
    0.42
    kter
    0.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.