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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Title
    -0.07
    -described
    -0.07
    Multip
    -0.06
    “These
    -0.06
    “When
    -0.06
    .slide
    -0.06
     furthermore
    -0.06
     Includes
    -0.06
    herence
    -0.06
    "As
    -0.06
    POSITIVE LOGITS
    席
    0.08
    _portfolio
    0.06
    _Header
    0.06
     się
    0.06
    日に
    0.06
     Custom
    0.06
    ouv
    0.06
     المص
    0.06
     projektu
    0.06
    ิหาร
    0.06
    Act Density 0.001%

    No Known Activations