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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prices
    -0.07
    かる
    -0.07
     Flame
    -0.07
    Doing
    -0.06
     needle
    -0.06
     amb
    -0.06
     Containers
    -0.06
     already
    -0.06
    xampp
    -0.06
    _tests
    -0.06
    POSITIVE LOGITS
     grilled
    0.07
     фор
    0.06
    .ToolStripButton
    0.06
    允
    0.06
    .ComponentResourceManager
    0.06
     Baz
    0.05
    					↵					↵
    0.05
     عبار
    0.05
    课
    0.05
    ，此
    0.05
    Act Density 0.007%

    No Known Activations