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

    Neuronpedia

    INDEX
    Explanations

    Liver health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dropdown
    -0.10
     Dropdown
    -0.10
     dropdown
    -0.09
    dropdown
    -0.09
    .dropdown
    -0.09
    (hand
    -0.08
     Heads
    -0.08
     Manhattan
    -0.08
    -dropdown
    -0.08
    袋
    -0.08
    POSITIVE LOGITS
     liver
    0.18
     hepatic
    0.17
     hepatitis
    0.15
     Liver
    0.15
     hepat
    0.15
     Hep
    0.13
     bilir
    0.12
     fibrosis
    0.12
     detox
    0.11
     печени
    0.11
    Act Density 0.026%

    No Known Activations