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

    Neuronpedia

    INDEX
    Explanations

    surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Administrator
    -0.07
     Maven
    -0.07
    OBJ
    -0.07
    ctr
    -0.07
     Eck
    -0.07
     concentr
    -0.06
    .XtraGrid
    -0.06
    cc
    -0.06
    world
    -0.06
     옥
    -0.06
    POSITIVE LOGITS
     surprise
    0.12
     surprises
    0.10
     surprised
    0.08
     surprising
    0.08
     persuade
    0.08
     překvap
    0.08
     Surprise
    0.07
     "~
    0.07
    .Pay
    0.07
     disappoint
    0.07
    Act Density 0.011%

    No Known Activations