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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     она
    0.49
     તેણીએ
    0.39
    she
    0.38
    让她
    0.38
    ！)
    0.38
     realising
    0.38
     she
    0.37
     utilising
    0.37
     realises
    0.36
     realisation
    0.36
    POSITIVE LOGITS
    Impl
    0.49
     $'
    0.44
     to
    0.43
     "
    0.42
     vo
    0.39
     "~/
    0.38
    avad
    0.38
     '"
    0.38
    Hav
    0.38
    ~$
    0.38
    Act Density 0.000%

    No Known Activations