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

    Neuronpedia

    INDEX
    Explanations

    mathematics and applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    辏
    0.51
    ார்
    0.49
     Unidas
    0.48
     έτσι
    0.48
    ভাঁ
    0.47
    ara
    0.47
     чыныгы
    0.47
     प्रमो
    0.46
     પોતાના
    0.46
    㶪
    0.46
    POSITIVE LOGITS
    _
    0.49
    }}+\
    0.44
    CTION
    0.42
    EQ
    0.41
    EV
    0.41
    >
    0.40
    :
    0.39
    />
    0.39
    EY
    0.39
    пель
    0.38
    Act Density 0.001%

    No Known Activations