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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prudent
    -0.07
    laps
    -0.07
    roduction
    -0.06
     lucr
    -0.06
     EVE
    -0.06
     donde
    -0.06
     lodged
    -0.06
     Uncle
    -0.06
    औ
    -0.06
    Euro
    -0.06
    POSITIVE LOGITS
    ertation
    0.08
    (tt
    0.07
    .isVisible
    0.06
    811
    0.06
    竞
    0.06
    /admin
    0.06
    igrations
    0.06
     (!(
    0.06
    _registered
    0.06
     scent
    0.06
    Act Density 0.005%

    No Known Activations