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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وک
    -0.07
     praised
    -0.06
     tournament
    -0.06
     rl
    -0.06
     schema
    -0.06
     mafia
    -0.06
     cartridge
    -0.06
     cages
    -0.06
    едера
    -0.06
     SUS
    -0.06
    POSITIVE LOGITS
     영상
    0.07
     νεφοκάλυψης
    0.06
    Authenticate
    0.06
     IEntity
    0.06
     выгляд
    0.06
    (dataset
    0.06
    -ip
    0.06
    UnitOfWork
    0.06
    '],$_
    0.06
    .tail
    0.06
    Act Density 0.022%

    No Known Activations