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

    Neuronpedia

    INDEX
    Explanations

    Theater productions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [('
    -0.07
    面积
    -0.07
     -*
    -0.06
     Nunes
    -0.06
    腰
    -0.06
     hemat
    -0.06
     Dre
    -0.06
    :{↵
    -0.06
     Dialogue
    -0.06
     wieder
    -0.06
    POSITIVE LOGITS
    Jan
    0.07
    prite
    0.06
    esterday
    0.06
    may
    0.06
     продуктов
    0.06
     적용
    0.06
    ικο
    0.06
    >#
    0.06
    알
    0.06
    escal
    0.06
    Act Density 0.004%

    No Known Activations