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

    Neuronpedia

    INDEX
    Explanations

    pandemic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ە
    0.96
    от
    0.95
     spectacle
    0.90
    اة
    0.87
     masterpiece
    0.86
    ității
    0.86
    হাওয়া
    0.86
    ất
    0.85
    кому
    0.85
    ه‌های
    0.85
    POSITIVE LOGITS
    其他
    0.95
    ज
    0.89
    𝗸
    0.88
    К
    0.87
    la
    0.85
    Ви
    0.82
    kker
    0.82
    𝘀
    0.81
    І
    0.80
    ஓ
    0.80
    Act Density 0.000%

    No Known Activations