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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nard
    -0.07
    _MONITOR
    -0.07
    _FRE
    -0.07
    UnitTest
    -0.07
     Yah
    -0.07
     (...)
    -0.07
    leriyle
    -0.07
     haya
    -0.06
     ابت
    -0.06
     Zah
    -0.06
    POSITIVE LOGITS
     classrooms
    0.06
     adjustable
    0.06
     PARA
    0.06
     Inventory
    0.06
    �
    0.06
     Substance
    0.06
    GLOBAL
    0.06
    regs
    0.06
     Locations
    0.05
    识
    0.05
    Act Density 0.001%

    No Known Activations