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

    Neuronpedia

    INDEX
    Explanations

    reviewing/revising

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dir
    -0.07
     tim
    -0.07
     Me
    -0.06
    Fund
    -0.06
     Slam
    -0.06
     mill
    -0.06
     Cosmetic
    -0.06
     lui
    -0.06
     Instruction
    -0.06
     Fund
    -0.06
    POSITIVE LOGITS
    λού
    0.07
    €™
    0.07
    ungen
    0.06
    _FB
    0.06
    StartElement
    0.06
    .springframework
    0.06
     gắn
    0.06
    \">"
    0.06
    .Localization
    0.06
     arquivo
    0.06
    Act Density 0.110%

    No Known Activations