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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    and
    0.37
    en
    0.31
    และ
    0.31
    និង
    0.30
     spectral
    0.30
    ong
    0.29
     Molecular
    0.29
    şa
    0.29
    the
    0.28
    et
    0.28
    POSITIVE LOGITS
     ingles
    0.31
     가
    0.28
     anderes
    0.28
    ANIEL
    0.28
    樂
    0.28
     acerca
    0.27
     normas
    0.27
     이어
    0.27
    ッ
    0.27
     demás
    0.26
    Act Density 0.599%

    No Known Activations