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

    Neuronpedia

    INDEX
    Explanations

    error messages/exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xcb
    -0.07
    ♖
    -0.07
     ![
    -0.07
    שם
    -0.07
    _daily
    -0.06
    ungkin
    -0.06
    ticks
    -0.06
    然是
    -0.06
     ",
↵
    -0.06
    SJ
    -0.06
    POSITIVE LOGITS
    借款
    0.07
    _stderr
    0.07
     stroll
    0.06
    杆
    0.06
     <+
    0.06
     Peek
    0.06
     erot
    0.06
     Moss
    0.06
     ethic
    0.06
    朦胧
    0.06
    Act Density 0.103%

    No Known Activations