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

    Neuronpedia

    INDEX
    Explanations

    disease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numar
    -0.07
    iator
    -0.06
     ponder
    -0.06
     shoulders
    -0.06
    .Inventory
    -0.06
     functools
    -0.06
    ultip
    -0.06
    Abr
    -0.06
     PPP
    -0.06
    .when
    -0.06
    POSITIVE LOGITS
     disease
    0.20
     Disease
    0.18
     diseases
    0.15
     Diseases
    0.11
     Dise
    0.09
     dise
    0.09
    isease
    0.09
    <Data
    0.08
    _DE
    0.08
    ease
    0.08
    Act Density 0.023%

    No Known Activations