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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     melhor
    -0.07
    フ
    -0.06
     republika
    -0.06
     gras
    -0.06
    ोफ
    -0.06
     protagonist
    -0.06
     Lý
    -0.06
    _detection
    -0.06
    fortunately
    -0.06
     markings
    -0.06
    POSITIVE LOGITS
     examined
    0.07
    овар
    0.07
     tours
    0.06
    (Constructor
    0.06
     enr
    0.06
     Topics
    0.06
    oldem
    0.06
    .HttpServletRequest
    0.06
     bail
    0.06
    (edge
    0.06
    Act Density 0.037%

    No Known Activations