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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    5
    -0.16
    6
    -0.14
    4
    -0.13
    7
    -0.13
    8
    -0.12
    3
    -0.11
     Five
    -0.09
     five
    -0.09
    2
    -0.09
    ۵
    -0.08
    POSITIVE LOGITS
    [file
    0.07
    くる
    0.06
     shoreline
    0.06
    <Q
    0.06
    ，请
    0.06
    .currentIndex
    0.06
    ～↵↵
    0.06
     scholarships
    0.06
    .readlines
    0.06
     pf
    0.06
    Act Density 0.297%

    No Known Activations