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

    Neuronpedia

    INDEX
    Explanations

    Code or foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egot
    -0.07
     tet
    -0.07
     Combine
    -0.07
    Between
    -0.07
    那
    -0.07
    mousedown
    -0.07
    昔
    -0.06
     aload
    -0.06
    あ
    -0.06
    原来的
    -0.06
    POSITIVE LOGITS
    issement
    0.08
    的重大
    0.07
     phá
    0.07
     capitalists
    0.07
     diferentes
    0.07
     Indie
    0.06
    研究成果
    0.06
    DK
    0.06
    .getProject
    0.06
    뗑
    0.06
    Act Density 0.099%

    No Known Activations