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

    Neuronpedia

    INDEX
    Explanations

    concentration camp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    โรค
    0.65
     சிகிச்ச
    0.61
    βο
    0.61
     ಸಹಾಯ
    0.60
    ებას
    0.59
     یورو
    0.59
     问题
    0.58
     پروژه
    0.57
     शौचालय
    0.57
    ড়ান্ত
    0.56
    POSITIVE LOGITS
     utilize
    0.70
    u
    0.68
    \
    0.64
    ne
    0.63
    the
    0.62
     Independ
    0.60
     Belling
    0.59
    জ
    0.59
     I
    0.59
     circulate
    0.57
    Act Density 0.001%

    No Known Activations