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

    Neuronpedia

    INDEX
    Explanations

    Gift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coverage
    -0.07
     buckle
    -0.07
     Decom
    -0.07
     attendees
    -0.07
    -night
    -0.07
     uptime
    -0.07
     Aurora
    -0.07
     novice
    -0.07
     truck
    -0.07
     bottom
    -0.07
    POSITIVE LOGITS
     gift
    0.17
     gifts
    0.14
     Gift
    0.13
    Gift
    0.12
     Gifts
    0.10
    gift
    0.09
    ift
    0.09
     gifted
    0.08
    bt
    0.07
    gt
    0.07
    Act Density 0.005%

    No Known Activations