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

    Neuronpedia

    INDEX
    Explanations

    numeric

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beast
    -0.07
     Serbia
    -0.07
     Classes
    -0.07
     flask
    -0.07
    ื่
    -0.07
    률
    -0.07
     Fields
    -0.07
     sembl
    -0.07
     lucky
    -0.07
    DDL
    -0.07
    POSITIVE LOGITS
    water
    0.08
     yup
    0.07
    可能存在
    0.07
     schematic
    0.07
    腈
    0.07
    often
    0.07
     vaping
    0.07
    液体
    0.07
    Mart
    0.07
     trò
    0.07
    Act Density 0.002%

    No Known Activations