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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     перепис
    -0.07
     Basics
    -0.07
    formats
    -0.06
    AffineTransform
    -0.06
     TimeUnit
    -0.06
    Success
    -0.06
     keep
    -0.06
    endimento
    -0.06
    minent
    -0.06
     Orientation
    -0.06
    POSITIVE LOGITS
    Não
    0.07
    (debug
    0.07
    iversite
    0.06
     Buddha
    0.06
    (ctx
    0.06
    SHARE
    0.06
     tomatoes
    0.06
     significantly
    0.06
     EntityManager
    0.06
     Tag
    0.06
    Act Density 0.120%

    No Known Activations