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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Toledo
    -0.08
    िष
    -0.08
     Zelda
    -0.08
     విషయ
    -0.08
    andom
    -0.08
     lugares
    -0.08
     చూడ
    -0.07
    Julie
    -0.07
     sorpresa
    -0.07
     Dinner
    -0.07
    POSITIVE LOGITS
     airport
    0.11
     Flughafen
    0.11
    'aéroport
    0.11
     aeropuerto
    0.10
     airports
    0.10
     aeroport
    0.09
    Entrance
    0.09
    Airport
    0.09
     entrance
    0.09
     elevators
    0.09
    Act Density 0.040%

    No Known Activations