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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Саша
    0.53
     </>
    0.52
     Алек
    0.49
     schöne
    0.49
     щоб
    0.48
     désormais
    0.48
     mostrar
    0.47
     {//
    0.46
     يس
    0.46
     naast
    0.46
    POSITIVE LOGITS
    udo
    0.54
    ிருந்து
    0.52
    is
    0.52
    Gang
    0.48
    old
    0.46
    active
    0.46
    Do
    0.44
    edge
    0.44
    高度
    0.44
    in
    0.43
    Act Density 0.002%

    No Known Activations