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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domina
    -0.07
    EndTime
    -0.07
     Edwin
    -0.06
     navbar
    -0.06
    文件
    -0.06
    Seconds
    -0.06
     heroine
    -0.06
     fonction
    -0.06
     shoots
    -0.06
     marry
    -0.06
    POSITIVE LOGITS
     Piece
    0.07
     Newsp
    0.07
    %)↵
    0.07
    506
    0.07
     inconsistent
    0.07
    dığ
    0.07
     ordinance
    0.07
    ManagedObjectContext
    0.06
     ---↵
    0.06
     Lambert
    0.06
    Act Density 0.062%

    No Known Activations