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

    Neuronpedia

    INDEX
    Explanations

    Code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    资格
    -0.08
     karena
    -0.08
     uptake
    -0.07
    コミュニ
    -0.07
    专业知识
    -0.07
    connect
    -0.07
     Quartz
    -0.07
    自习
    -0.07
     Huffman
    -0.07
     Diss
    -0.07
    POSITIVE LOGITS
    holm
    0.07
    *B
    0.07
     VBox
    0.07
     Cur
    0.07
    $t
    0.07
    ific
    0.07
     gab
    0.07
    מהירות
    0.07
    (stypy
    0.06
    irical
    0.06
    Act Density 0.084%

    No Known Activations