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

    Neuronpedia

    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medicine
    -1.18
     Medicine
    -1.11
     MEDICINE
    -1.06
    medicine
    -0.98
    Medicine
    -0.96
    AddTagHelper
    -0.78
    medizin
    -0.78
     saites
    -0.76
     medicina
    -0.75
    orteur
    -0.72
    POSITIVE LOGITS
     use
    0.55
    <bos>
    0.47
     usage
    0.47
    SC
    0.46
    F
    0.43
    S
    0.41
     brancas
    0.41
     to
    0.41
     wear
    0.40
    angsaan
    0.40
    Act Density 0.011%

    No Known Activations