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

    Neuronpedia

    INDEX
    Explanations

    image file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acidosis
    0.59
     pathophys
    0.57
     sintomi
    0.57
     diarrh
    0.56
    🧠
    0.56
    mRNA
    0.55
     prostagland
    0.54
    DMSO
    0.54
    jahter
    0.54
     transcriptional
    0.54
    POSITIVE LOGITS
     images
    1.47
     image
    1.44
    图片
    1.39
     Image
    1.38
     Images
    1.31
    图像
    1.30
    Image
    1.27
    圖片
    1.26
     изображения
    1.25
    图片的
    1.25
    Act Density 0.256%

    No Known Activations