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

    Neuronpedia

    INDEX
    Explanations

    temperature regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }&\
    0.43
    冷静
    0.40
     פע
    0.37
    ㎎
    0.37
     กม
    0.37
    0.37
    ("_
    0.36
    0.36
    0.36
    ల్‌
    0.35
    POSITIVE LOGITS
     Blood
    0.48
     .
    0.48
     amber
    0.41
     baby
    0.40
     expect
    0.40
     classifying
    0.40
     rosemary
    0.39
     rhino
    0.39
     Butter
    0.39
     pork
    0.39
    Act Density 0.000%

    No Known Activations