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

    Neuronpedia

    INDEX
    Explanations

    Enron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     객체
    -0.08
     aluno
    -0.07
    amaha
    -0.07
    elters
    -0.07
     spoiled
    -0.07
    Gre
    -0.06
     camper
    -0.06
     obsessed
    -0.06
     주요
    -0.06
     tablets
    -0.06
    POSITIVE LOGITS
     characteristic
    0.08
     chữ
    0.07
    tan
    0.06
     chapter
    0.06
    nn
    0.06
    jan
    0.06
    acting
    0.06
     neatly
    0.06
    特别
    0.06
     ray
    0.06
    Act Density 0.002%

    No Known Activations