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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %X
    -0.07
     KB
    -0.07
     Nu
    -0.07
     róż
    -0.07
     Toplam
    -0.07
    to
    -0.06
     nawet
    -0.06
    (DbContext
    -0.06
    =input
    -0.06
     harmless
    -0.06
    POSITIVE LOGITS
    릴
    0.07
     Fever
    0.07
    .ForegroundColor
    0.06
    Toggle
    0.06
    -agent
    0.06
    .walk
    0.06
    <State
    0.06
    atherine
    0.06
    ''↵
    0.06
     crawl
    0.06
    Act Density 0.005%

    No Known Activations