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

    Neuronpedia

    INDEX
    Explanations

    lists of ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     прият
    0.54
     고려
    0.48
     பிர
    0.46
     при
    0.46
    东南
    0.46
     හොඳ
    0.46
    ่
    0.45
     तमिल
    0.45
     colorChoice
    0.45
     吴
    0.44
    POSITIVE LOGITS
    0.57
     Marxism
    0.50
    '
    0.48
     PHYSICS
    0.46
    clicked
    0.45
    manifold
    0.44
     dizziness
    0.44
    medicine
    0.44
     glaciers
    0.44
    water
    0.43
    Act Density 0.002%

    No Known Activations