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

    Neuronpedia

    INDEX
    Explanations

    fill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .borderWidth
    -0.07
    缆
    -0.07
     defendant
    -0.06
     bites
    -0.06
    比重
    -0.06
    群
    -0.06
    面对
    -0.06
    _cli
    -0.06
     imagen
    -0.06
    Solution
    -0.06
    POSITIVE LOGITS
     Chrysler
    0.08
     getCategory
    0.08
    .One
    0.07
     redemption
    0.06
    reek
    0.06
    ၵ
    0.06
     understands
    0.06
    七个
    0.06
     rode
    0.06
     prere
    0.06
    Act Density 0.001%

    No Known Activations