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

    Neuronpedia

    INDEX
    Explanations

    number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _vel
    -0.07
     swarm
    -0.07
    iscard
    -0.07
    ümüzde
    -0.06
    _words
    -0.06
     owned
    -0.06
    Mountain
    -0.06
     мон
    -0.06
     ELSE
    -0.06
    leys
    -0.06
    POSITIVE LOGITS
     felon
    0.06
    �
    0.06
    DR
    0.06
     armed
    0.06
     luận
    0.06
    .Calendar
    0.06
    USES
    0.06
     orally
    0.05
     xã
    0.05
     عاما
    0.05
    Act Density 0.019%

    No Known Activations