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

    Neuronpedia

    INDEX
    Explanations

    password security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sex
    -0.07
     öne
    -0.06
    æ
    -0.06
     chuyến
    -0.06
     ride
    -0.06
     runners
    -0.06
    ande
    -0.06
     şart
    -0.06
     runner
    -0.06
    joined
    -0.06
    POSITIVE LOGITS
     NASA
    0.08
     év
    0.07
    fill
    0.06
    AndFeel
    0.06
     HEAP
    0.06
    .Now
    0.06
     prům
    0.06
     uranus
    0.06
    HTTPRequest
    0.06
     Northern
    0.06
    Act Density 0.019%

    No Known Activations