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

    Neuronpedia

    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    层
    -0.08
     Human
    -0.07
     harvesting
    -0.07
     cubic
    -0.07
     message
    -0.07
     Mara
    -0.07
    lope
    -0.07
     defeat
    -0.06
     cable
    -0.06
    /dialog
    -0.06
    POSITIVE LOGITS
     اولین
    0.06
     تاثیر
    0.06
    简单
    0.06
    .btnClose
    0.06
    ليه
    0.06
     smtp
    0.06
    svn
    0.06
     lassen
    0.06
     boldly
    0.06
    ,(
    0.06
    Act Density 0.091%

    No Known Activations