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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    meni
    -0.07
     mey
    -0.07
     DEN
    -0.07
    iid
    -0.06
    ό
    -0.06
     nutzen
    -0.06
    je
    -0.06
    	build
    -0.06
     Vil
    -0.06
     DataLoader
    -0.06
    POSITIVE LOGITS
    iques
    0.07
     cosm
    0.06
    :NSLocalizedString
    0.06
     adherence
    0.06
     suffer
    0.06
    	setTimeout
    0.06
    .Sequential
    0.06
    作者
    0.06
    'in
    0.06
    atin
    0.06
    Act Density 0.089%

    No Known Activations