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

    Neuronpedia

    INDEX
    Explanations

    Cancer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optim
    -0.07
     Nigel
    -0.06
    ：“
    -0.06
    .is
    -0.06
     totalitarian
    -0.06
    	day
    -0.06
     主
    -0.06
    ん
    -0.06
    _literal
    -0.06
    PDOException
    -0.06
    POSITIVE LOGITS
    štění
    0.07
    ABEL
    0.07
    forest
    0.06
    )new
    0.06
    gium
    0.06
    ListView
    0.06
    esub
    0.06
    tem
    0.06
    526
    0.06
    лені
    0.06
    Act Density 0.006%

    No Known Activations