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

    Neuronpedia

    INDEX
    Explanations

    neither X nor Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     documentaries
    0.39
    స్తుంది
    0.36
    ენტის
    0.36
     философии
    0.35
    ೃತ
    0.35
    স্তন
    0.34
     sécr
    0.34
    गेशन
    0.34
    त्रेयी
    0.34
    詬
    0.34
    POSITIVE LOGITS
    這些
    0.37
     These
    0.37
    These
    0.37
    这些
    0.37
    これらの
    0.36
     Эти
    0.35
     இவற்ற
    0.33
    these
    0.33
    Bol
    0.33
    やつ
    0.33
    Act Density 0.001%

    No Known Activations