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

    Neuronpedia

    INDEX
    Explanations

    seats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sözleş
    -0.07
     UIAlertView
    -0.07
    optimizer
    -0.07
     empt
    -0.06
    phinx
    -0.06
    (student
    -0.06
    ộc
    -0.06
    واع
    -0.06
    _intervals
    -0.06
     alumni
    -0.06
    POSITIVE LOGITS
     Dogs
    0.08
     dragged
    0.07
     degradation
    0.07
     Dealers
    0.06
     relationship
    0.06
     GetString
    0.06
    /social
    0.06
     upkeep
    0.06
     Auto
    0.06
     paragraph
    0.06
    Act Density 0.008%

    No Known Activations