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

    Neuronpedia

    INDEX
    Explanations

    code comment delimiters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    生产企业
    -0.07
     dip
    -0.06
     lightly
    -0.06
     jets
    -0.06
    chy
    -0.06
     Recycling
    -0.06
     Elsa
    -0.06
     globe
    -0.06
    your
    -0.06
    jąc
    -0.06
    POSITIVE LOGITS
    .GroupBox
    0.08
    successful
    0.08
    主动
    0.07
     оказа
    0.07
    transform
    0.07
    ANCES
    0.07
    Navigator
    0.07
    פעולות
    0.07
    見積もり
    0.07
     attempting
    0.07
    Act Density 0.004%

    No Known Activations