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

    Neuronpedia

    INDEX
    Explanations

    announcements and debuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ですから
    0.50
     grandeza
    0.49
     ανθρώ
    0.45
     barbit
    0.44
     판단
    0.43
     PubMed
    0.42
     grandeur
    0.42
     voulez
    0.42
     incompar
    0.41
     edific
    0.41
    POSITIVE LOGITS
     annoncé
    0.70
     announced
    0.66
    umumkan
    0.59
    ২০
    0.57
     anunció
    0.57
     debuted
    0.55
     erneut
    0.55
     anunciou
    0.55
     পুনরায়
    0.54
     debuting
    0.54
    Act Density 0.001%

    No Known Activations