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

    Neuronpedia

    INDEX
    Explanations

    game controls axis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    酪
    -0.07
     Managed
    -0.07
    (listener
    -0.07
     podcast
    -0.07
     BuzzFeed
    -0.07
    /check
    -0.06
    绿豆
    -0.06
     spotted
    -0.06
     PW
    -0.06
     eventId
    -0.06
    POSITIVE LOGITS
    allen
    0.08
    �
    0.07
    lyn
    0.07
    sets
    0.07
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.07
    bt
    0.06
     nat
    0.06
    кле
    0.06
    reib
    0.06
     citizenship
    0.06
    Act Density 0.025%

    No Known Activations