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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     נ
    0.48
     an
    0.47
    的的
    0.47
    ɡ
    0.46
    )$;
    0.46
     n
    0.44
    ન્યા
    0.44
     the
    0.43
     който
    0.43
    }}$,
    0.43
    POSITIVE LOGITS
     técnicas
    0.68
     Advocacy
    0.61
    ™.
    0.60
     assistência
    0.59
     konusunda
    0.59
     établissements
    0.59
     Vox
    0.58
    даг
    0.58
     compartió
    0.57
     dakkh
    0.57
    Act Density 0.006%

    No Known Activations