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

    Neuronpedia

    INDEX
    Explanations

    Goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    archical
    -0.07
     EventBus
    -0.06
     billionaires
    -0.06
    ashboard
    -0.06
    /png
    -0.06
     boosts
    -0.06
     tighten
    -0.06
    Elite
    -0.06
    ╗
    -0.06
    Streamer
    -0.06
    POSITIVE LOGITS
    рек
    0.07
     доб
    0.07
     cruising
    0.07
    roupon
    0.06
    粗
    0.06
     "?
    0.06
     생
    0.06
    лия
    0.06
     tokenId
    0.06
     oči
    0.06
    Act Density 0.017%

    No Known Activations