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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     También
    1.58
     Qxd
    1.45
     bhave
    1.37
     Litter
    1.29
    nomina
    1.26
     Ciencias
    1.26
     вой
    1.24
     Median
    1.23
     ciencias
    1.22
     denitr
    1.21
    POSITIVE LOGITS
    ט
    1.34
    ו
    1.17
    an
    1.08
    as
    1.08
    at
    1.07
    en
    1.04
    𝘢
    1.02
    onError
    0.99
    т
    0.97
    ು
    0.97
    Act Density 0.000%

    No Known Activations