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

    Neuronpedia

    INDEX
    Explanations

    DataCamp or FreeCodeCamp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    朤
    0.55
    टीना
    0.53
     вікі
    0.52
     الإلكتر
    0.52
     प्रभावशाली
    0.52
    टरनेट
    0.51
     ገን
    0.51
     الأز
    0.51
     Lobkovic
    0.51
    मिटेड
    0.51
    POSITIVE LOGITS
    ---
    0.59
    1
    0.59
    ↵
    0.57
     according
    0.55
    m
    0.54
    根据
    0.53
     of
    0.53
        
    0.52
    9
    0.51
    사
    0.51
    Act Density 0.001%

    No Known Activations