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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ین
    1.17
    plic
    1.14
    1
    0.98
     Adder
    0.97
    ge
    0.97
    keras
    0.96
     lauf
    0.96
    2
    0.95
     lal
    0.94
    cl
    0.91
    POSITIVE LOGITS
    маты
    1.18
    unakan
    1.14
    𐰃
    1.14
     प्रकारे
    1.10
    1.10
     entreprise
    1.09
     viszont
    1.07
     Cependant
    1.07
     তাতে
    1.07
     عالية
    1.06
    Act Density 0.000%

    No Known Activations