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

    Neuronpedia

    INDEX
    Explanations

    body temperature symptom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    1.07
    ก
    1.05
    ן
    0.92
    thed
    0.91
    هم
    0.91
    smanship
    0.91
    त
    0.86
    ल
    0.85
    ל
    0.85
    لای
    0.84
    POSITIVE LOGITS
    2
    1.06
     Fever
    0.93
     fever
    0.86
    ↵↵
    0.80
     fiebre
    0.80
    ON
    0.74
    3
    0.74
     fièvre
    0.74
    5
    0.74
    ﺭ
    0.73
    Act Density 0.002%

    No Known Activations