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

    Neuronpedia

    INDEX
    Explanations

    autoimmune diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.57
     TextView
    0.48
    -
    0.47
     genannten
    0.45
     zweiten
    0.45
     diejenigen
    0.44
    /,
    0.42
    =
    0.42
    $/,
    0.41
    接下來
    0.40
    POSITIVE LOGITS
    Infrastructure
    0.59
    toxic
    0.54
    infrastructure
    0.54
    医药
    0.52
     agricultura
    0.50
     toxicology
    0.49
     carcinogenic
    0.47
    蛋白质
    0.47
    cią
    0.46
     ασ
    0.46
    Act Density 0.076%

    No Known Activations