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

    Neuronpedia

    INDEX
    Explanations

    durability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addons
    -0.07
    acid
    -0.06
     playlist
    -0.06
    _LIST
    -0.06
    discard
    -0.06
     playlists
    -0.06
    界
    -0.06
    appear
    -0.06
    FAILED
    -0.06
    _NO
    -0.06
    POSITIVE LOGITS
     recommends
    0.07
    PFN
    0.06
     Celtics
    0.06
     informant
    0.06
     Man
    0.06
     presup
    0.06
    /end
    0.06
     publicity
    0.06
    \Core
    0.06
     Tại
    0.06
    Act Density 0.038%

    No Known Activations